© 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. 16-GEMMASCOPE-2-RES-16K
    7. 486
    Prev
    Next
    INDEX
    Explanations

    good followed by noun

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

    best way

    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_16_width_16k_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
    0.78
    ’
    0.76
    '
    0.69
    ’;
    0.64
    ના
    0.63
    </span>
    0.59
     seagulls
    0.59
    ׳
    0.59
    ()'
    0.58
    s
    0.57
    POSITIVE LOGITS
    in
    0.70
    inę
    0.64
    inney
    0.63
    inning
    0.59
    inna
    0.56
    ilat
    0.56
    inį
    0.55
    inium
    0.54
    inama
    0.54
    inum
    0.53
    Activations Density 1.470%

    No Known Activations