© 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. 210621
    Prev
    Next
    INDEX
    Explanations

    appeared / appear

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

    stunning, unique, sure, Valor, guarding, should

    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
    帆
    0.43
    思想
    0.42
     verb
    0.41
    更多
    0.41
    "
    0.40
    LINE
    0.40
    倡
    0.40
     চিন্তা
    0.40
    勸
    0.40
    ^(
    0.39
    POSITIVE LOGITS
     தொற்று
    0.57
    வதற்காக
    0.54
    BackButton
    0.52
     Wasserstein
    0.51
    phenoxymethyl
    0.51
    лізації
    0.50
    hydrocèle
    0.50
    MediaPath
    0.50
    らなかった
    0.50
    addena
    0.49
    Activations Density 0.001%

    No Known Activations