© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14056
    Prev
    Next
    INDEX
    Explanations

    expressing or reporting issues

    np_acts-logits-general · gemini-2.5-flash-lite

    speaking or signaling

    np_acts-logits-general · gemini-2.5-flash-lite

    reported speech or complaints

    np_max-act-logits · claude-4-5-sonnetTriggered by @sripadkarne
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bahawa
    0.63
     bahwa
    0.59
     mengatakan
    0.55
    :“
    0.54
     заявил
    0.54
     మాట్లాడుతూ
    0.52
     заяви
    0.51
     сказал
    0.51
     сказала
    0.50
     rằng
    0.50
    POSITIVE LOGITS
     +
    0.55
     geometries
    0.44
     implements
    0.42
     functionalities
    0.42
     linearly
    0.41
     optimizes
    0.40
     operable
    0.40
    -,
    0.39
    -/
    0.39
     blocks
    0.39
    Activations Density 0.084%

    No Known Activations