© 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. 216395
    Prev
    Next
    INDEX
    Explanations

    Did questions or reality

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

    Birth, fate, beware, enforcement, rewrite

    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
    a
    0.66
    io
    0.55
     déclaré
    0.53
    n
    0.50
    ni
    0.49
    wa
    0.48
    lan
    0.48
     bain
    0.47
    id
    0.47
    se
    0.46
    POSITIVE LOGITS
    ப்பட்டது
    0.49
    疃
    0.47
     तेरी
    0.47
     учены
    0.45
     امید
    0.45
    かけた
    0.44
     apprehension
    0.44
     modalCard
    0.43
    CriteriaUtils
    0.41
     منصوبہ
    0.41
    Activations Density 0.000%

    No Known Activations