© 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. 216837
    Prev
    Next
    INDEX
    Explanations

    instructions and rules

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

    battle tendency, sidecar, research project

    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
    ↵↵
    0.53
    <0x0D>
    0.51
    ungal
    0.49
     Them
    0.47
     Low
    0.46
    itary
    0.43
     THEM
    0.43
    onat
    0.43
    z
    0.42
     Which
    0.42
    POSITIVE LOGITS
    ະພັນ
    0.49
    궬
    0.48
     readable
    0.47
     defended
    0.46
    탰
    0.46
    leme
    0.46
    Noeud
    0.45
     internalized
    0.45
    㖣
    0.45
    ઉસ
    0.44
    Activations Density 0.001%

    No Known Activations