© 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. 155013
    Prev
    Next
    INDEX
    Explanations

    business contact information and services

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

    predicting words like mat

    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
    nętr
    0.55
    椎
    0.54
    hemia
    0.50
    ađ
    0.50
     მათ
    0.47
    jetas
    0.46
    iria
    0.46
    aditional
    0.46
    न्ध
    0.46
    씩
    0.45
    POSITIVE LOGITS
    6
    0.56
    4
    0.54
    0
    0.48
    9
    0.48
    3
    0.46
     aa
    0.46
    8
    0.46
     a
    0.46
     off
    0.46
     mi
    0.46
    Activations Density 0.000%

    No Known Activations