© 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. 97171
    Prev
    Next
    INDEX
    Explanations

    accepts explanation, weight capacity, TM volume, no spam, kids are, female driving

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

    concepts followed by consequences

    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
     assent
    0.48
    ikum
    0.43
    0.43
     vass
    0.42
     (
    0.42
     svoj
    0.41
     {
    0.41
     savo
    0.41
    дав
    0.41
     CREATE
    0.41
    POSITIVE LOGITS
     பெருமா
    0.53
     নিশ্চয়
    0.51
    p
    0.49
     priorité
    0.47
    in
    0.46
     ሞ
    0.46
    独特
    0.45
     পেয়েছিলাম
    0.45
     खतरा
    0.44
     méthodes
    0.43
    Activations Density 0.001%

    No Known Activations