© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 102379
    Prev
    Next
    INDEX
    Explanations

    services and activities

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

    fall of empires

    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
    Ḵ
    0.56
    ádiz
    0.50
     klubu
    0.45
    erland
    0.44
    委員會
    0.44
    Zv
    0.44
     dSample
    0.43
    אל
    0.43
     pô
    0.43
     válv
    0.43
    POSITIVE LOGITS
     HIV
    0.58
     RGB
    0.50
     HIPAA
    0.49
     Feed
    0.48
     beak
    0.48
     P
    0.47
     Expression
    0.47
     For
    0.47
     Jim
    0.47
     hiv
    0.47
    Activations Density 0.001%

    No Known Activations