© 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. 219115
    Prev
    Next
    INDEX
    Explanations

    fixed, improved, long term

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

    poke effectively

    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
     efter
    0.55
     ใ
    0.52
     rc
    0.49
    🏄
    0.48
     trapez
    0.47
     legy
    0.47
     T
    0.46
     köş
    0.46
     selon
    0.46
     După
    0.46
    POSITIVE LOGITS
     காலம்
    0.45
    ledger
    0.44
    稼
    0.44
    ventional
    0.42
     منهج
    0.41
    justice
    0.40
    действие
    0.40
    膽
    0.40
    actment
    0.39
    сі
    0.39
    Activations Density 0.000%

    No Known Activations