© 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. 49365
    Prev
    Next
    INDEX
    Explanations

    interested in

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

    interested in

    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
     xưa
    0.49
    需要
    0.49
    都要
    0.49
     voorzien
    0.47
     ’
    0.47
     mangrove
    0.47
     पड़ने
    0.45
     PAM
    0.45
     đang
    0.44
     lending
    0.44
    POSITIVE LOGITS
    Brazilian
    0.45
    ucer
    0.45
    istatic
    0.44
    cled
    0.43
    場合は
    0.43
    icarbon
    0.43
     または
    0.43
    ૂ
    0.43
    नमस्कार
    0.43
    czek
    0.43
    Activations Density 0.002%

    No Known Activations