© 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. 101398
    Prev
    Next
    INDEX
    Explanations

    foreign words

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

    multiple options or sequences

    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
    飧
    0.50
    ί
    0.49
    <0xAD>
    0.49
    पै
    0.48
    हाबाद
    0.47
    пы
    0.46
    ùa
    0.46
     hanging
    0.46
    ocardial
    0.46
    idity
    0.46
    POSITIVE LOGITS
     mehrerer
    0.56
     hopp
    0.46
     lawe
    0.46
     nennt
    0.45
    ダーク
    0.45
     prij
    0.44
     לפני
    0.44
     Weltkrieg
    0.44
     黒
    0.44
     மக்க
    0.43
    Activations Density 0.000%

    No Known Activations