© 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. 69072
    Prev
    Next
    INDEX
    Explanations

    First words, surprise visits, act accordingly, shift system

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

    especially, then, that, for

    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
    ibilities
    0.47
    ltre
    0.44
     त्यांची
    0.43
    tv
    0.42
    늘
    0.41
    कत
    0.41
     त्याची
    0.41
     headquarters
    0.41
    quit
    0.40
     그리고
    0.40
    POSITIVE LOGITS
     Ign
    0.44
    嬂
    0.43
    应用于
    0.43
     entière
    0.43
     Battlefield
    0.41
     religión
    0.41
     zawier
    0.41
     anses
    0.41
     deoarece
    0.41
     علامه
    0.40
    Activations Density 0.000%

    No Known Activations