© 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. 121710
    Prev
    Next
    INDEX
    Explanations

    progress and distance

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

    Spanish and English mixed

    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
     dniu
    0.56
     captured
    0.49
     drained
    0.49
    клон
    0.47
     cloned
    0.46
     відо
    0.46
     depleted
    0.45
    ၺ
    0.45
     DWORD
    0.44
     аны
    0.44
    POSITIVE LOGITS
    UNT
    0.55
    atay
    0.48
    ANTS
    0.46
    MSS
    0.44
     ترقی
    0.42
    IC
    0.41
    进步
    0.41
    进展
    0.41
     Progress
    0.41
    tay
    0.40
    Activations Density 0.001%

    No Known Activations