© 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. 136428
    Prev
    Next
    INDEX
    Explanations

    names of celestial bodies

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

    influences cell behavior

    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
     सेकंड
    0.42
     newValue
    0.42
     Parliament
    0.41
    တဲ့
    0.41
    ंडा
    0.41
    は約
    0.40
    <unused90>
    0.40
     Russian
    0.40
     l
    0.39
     inputValue
    0.39
    POSITIVE LOGITS
    cares
    0.52
    CCE
    0.50
    particip
    0.49
    CE
    0.47
    fle
    0.47
    rollers
    0.47
    CC
    0.46
    iry
    0.46
    чных
    0.46
    kumar
    0.46
    Activations Density 0.000%

    No Known Activations