© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 15072
    Prev
    Next
    INDEX
    Explanations

    energy, impact, reliability, scarcity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
    ؛
    0.80
    ;<
    0.73
    ;
    0.70
     మరియు
    0.66
    ;
    0.64
     disasters
    0.63
    ;,
    0.63
     катастро
    0.63
     và
    0.62
    ,【
    0.62
    POSITIVE LOGITS
    ContentType
    0.75
     একটা
    0.72
    こういう
    0.68
    ൊരു
    0.66
     ਇੱਕ
    0.62
    볕
    0.62
    vitamin
    0.61
    来自
    0.61
    Refresh
    0.60
    BODY
    0.60
    Activations Density 0.168%

    No Known Activations