© 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. 132768
    Prev
    Next
    INDEX
    Explanations

    about this matter

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

    explaining why

    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
    𝔱
    0.53
     つい
    0.50
     まず
    0.50
     घरवालों
    0.50
     Goliath
    0.49
     カラー
    0.49
     Thierry
    0.48
     Antony
    0.48
    Ｓ
    0.48
     hounds
    0.47
    POSITIVE LOGITS
    Append
    0.56
    cups
    0.49
    bec
    0.48
    useful
    0.48
    ou
    0.47
    Cups
    0.47
    е
    0.47
    um
    0.45
    con
    0.45
    jeta
    0.45
    Activations Density 0.000%

    No Known Activations