© 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. 194051
    Prev
    Next
    INDEX
    Explanations

    disastrous decisions following

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

    systems and achievements

    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
     outcrop
    0.48
     enfin
    0.46
    🚇
    0.46
    agge
    0.45
    🎆
    0.45
    ’;
    0.45
    }@
    0.44
     تاريخ
    0.44
    ڄ
    0.44
     Gemä
    0.43
    POSITIVE LOGITS
    魃
    0.46
    करें
    0.43
    上げる
    0.42
     RULE
    0.41
     antih
    0.40
     silence
    0.40
     tossing
    0.39
     legislatures
    0.39
     absc
    0.39
    प्र
    0.39
    Activations Density 0.001%

    No Known Activations