© 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. 40202
    Prev
    Next
    INDEX
    Explanations

    news headlines and reports

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

    news headlines and abbreviations

    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
     మరియు
    0.63
    为什么
    0.58
    为什么要
    0.56
     shockingly
    0.55
    the
    0.54
     आणि
    0.52
     ‎
    0.52
     has
    0.51
     (!)
    0.51
     এবং
    0.50
    POSITIVE LOGITS
    揆
    0.57
     pptn
    0.55
     solns
    0.54
     물론
    0.52
     plupart
    0.51
     expts
    0.50
     derivs
    0.50
     probs
    0.49
    Ꮲ
    0.47
     ilk
    0.46
    Activations Density 0.012%

    No Known Activations