© 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. 217754
    Prev
    Next
    INDEX
    Explanations

    hereby disclaims and negates

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

    hierarchy and targeting

    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
    simulation
    0.46
    ského
    0.45
    ny
    0.44
     starred
    0.44
    eteers
    0.44
    v
    0.43
    senz
    0.43
    notation
    0.43
    nik
    0.42
    seg
    0.42
    POSITIVE LOGITS
     keySchedule
    0.48
     Kindergarten
    0.47
     கொண்டது
    0.45
    𝙠
    0.45
     chemicals
    0.44
    幼儿
    0.44
    利亚
    0.43
     tangy
    0.43
     tornadoes
    0.43
     الاي
    0.42
    Activations Density 0.000%

    No Known Activations