© 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. 175909
    Prev
    Next
    INDEX
    Explanations

    freezer and hunk

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

    task completion or specific formatting

    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
     neuropathy
    0.47
     블루
    0.46
    <0x8F>
    0.46
     hoàng
    0.46
     mellow
    0.45
     अम्ल
    0.44
     Model
    0.44
     협
    0.44
     Petsc
    0.44
     tongue
    0.44
    POSITIVE LOGITS
    arod
    0.46
     benutzer
    0.46
     মুখপাত্র
    0.45
    arity
    0.45
    polit
    0.44
    reto
    0.44
    riott
    0.43
     envio
    0.43
    awed
    0.43
    രുവന
    0.43
    Activations Density 0.000%

    No Known Activations