© 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. 166228
    Prev
    Next
    INDEX
    Explanations

    relationship and qualities

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

    looking forward

    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
     guiclass
    0.54
     कराने
    0.48
     చేసే
    0.47
     Nasıl
    0.46
     ఎలా
    0.45
     其
    0.45
     dessen
    0.45
     ముందు
    0.44
     Grupo
    0.44
     問題
    0.44
    POSITIVE LOGITS
     pratiques
    0.47
    EDED
    0.47
    ود
    0.46
    🖕
    0.44
    ੁਰ
    0.42
    ור
    0.41
    作品
    0.41
    ਣਾ
    0.41
    ܙ
    0.41
    ומר
    0.40
    Activations Density 0.000%

    No Known Activations