© 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. 234282
    Prev
    Next
    INDEX
    Explanations

    sizes shown below

    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
     corrupted
    0.57
     entornos
    0.54
     enfermos
    0.49
     crashes
    0.47
     annan
    0.46
    詆
    0.46
     backgrounds
    0.46
     ambientes
    0.46
    ❕
    0.46
    <unused565>
    0.46
    POSITIVE LOGITS
    text
    0.65
    can
    0.56
    low
    0.55
    sc
    0.55
    she
    0.55
    submit
    0.55
    size
    0.55
    sa
    0.55
    active
    0.55
    eight
    0.54
    Activations Density 0.000%

    No Known Activations