© 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. 223442
    Prev
    Next
    INDEX
    Explanations

    compatible with, groups, Connecticut, schematic, abutted

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

    height and measurements

    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
    दुर्
    0.51
     visual
    0.46
    field
    0.46
     N
    0.46
     Jackson
    0.46
     Children
    0.45
     Father
    0.45
    d
    0.44
     Ch
    0.44
    imag
    0.44
    POSITIVE LOGITS
    ющим
    0.50
    поряд
    0.49
    žena
    0.49
    সম্পাদকীয়
    0.48
    蛉
    0.47
    गतान
    0.46
    ಹಾಸ
    0.44
    頎
    0.44
    ρα
    0.44
    蘄
    0.44
    Activations Density 0.001%

    No Known Activations