© 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. 13869
    Prev
    Next
    INDEX
    Explanations

    specific word sequences

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

    https links

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

    personal narratives

    np_max-act-logits · claude-4-5-sonnetTriggered by @sk5695
    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
     It
    0.54
    :
    0.54
    /
    0.51
     (
    0.50
     objekt
    0.42
     تعالى
    0.41
     بما
    0.41
     Gere
    0.41
    -
    0.41
     Pacheco
    0.40
    POSITIVE LOGITS
    ي
    0.54
    。</
    0.53
    ρων
    0.53
    myLabels
    0.50
    ে
    0.49
    𝗷
    0.49
    νος
    0.47
     নিঃসৃত
    0.47
    欝
    0.47
    菪
    0.46
    Activations Density 0.883%

    No Known Activations