© 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. 46162
    Prev
    Next
    INDEX
    Explanations

    negative or specific entities

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

    potential targeted

    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
    сына
    0.51
    崬
    0.43
    椏
    0.42
    িনি
    0.42
    ক্রম
    0.42
    νε
    0.42
    ὡ
    0.42
    十二
    0.41
    ир
    0.41
    оні
    0.41
    POSITIVE LOGITS
     Schaden
    0.51
     Cheat
    0.50
     tzv
    0.49
     Sancho
    0.47
     wrongly
    0.47
     automatically
    0.46
     crashed
    0.46
     fraudulently
    0.46
     Anfield
    0.45
     diciamo
    0.45
    Activations Density 0.000%

    No Known Activations