© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 138235
    Prev
    Next
    INDEX
    Explanations

    fishing, custom products, and events

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

    deposits, factors, application, beans, intent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     店
    0.53
     *****
    0.49
     elephant
    0.47
     eccentric
    0.46
    榉
    0.46
    σιά
    0.45
     ******
    0.44
     Edinburgh
    0.44
     inspect
    0.44
     EVA
    0.44
    POSITIVE LOGITS
    ℓ
    0.55
    d
    0.52
    Q
    0.50
    SCALE
    0.50
    AUDIO
    0.50
    U
    0.50
    å
    0.48
    dj
    0.47
    X
    0.47
    ன
    0.47
    Activations Density 0.000%

    No Known Activations