© 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. 177916
    Prev
    Next
    INDEX
    Explanations

    Supplement plan, desired deactivation, threatened by

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

    instruction completion

    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
    ↵
    0.49
     two
    0.49
     l
    0.48
     precarious
    0.48
    Reads
    0.48
     finns
    0.47
     writes
    0.46
    Writes
    0.46
     P
    0.46
     t
    0.45
    POSITIVE LOGITS
    чнай
    0.52
    酲
    0.52
     endroits
    0.49
    ولو
    0.48
     appareils
    0.48
     CORPER
    0.48
    헿
    0.48
    ⴳ
    0.47
    ική
    0.46
    າມາດ
    0.46
    Activations Density 0.001%

    No Known Activations