© 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. 130521
    Prev
    Next
    INDEX
    Explanations

    accomplish then

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

    tts, medical, security, business

    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
     universidades
    0.47
    processors
    0.46
     prothorace
    0.44
     principalColumn
    0.44
    袤
    0.44
     interstitiis
    0.43
    ensureEqual
    0.43
    न्वयन
    0.43
     yattha
    0.43
    க்கொ
    0.42
    POSITIVE LOGITS
    AZ
    0.54
    AL
    0.51
    UNIT
    0.50
    AY
    0.49
    Psy
    0.49
    0.49
    Psych
    0.49
     장
    0.49
    AX
    0.48
    _
    0.48
    Activations Density 0.000%

    No Known Activations