© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 12-GEMMASCOPE-2-RES-16K
    7. 50
    Prev
    Next
    INDEX
    Explanations

    numbers or counts

    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_12_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
    s
    0.82
    𝐬
    0.65
    𝐭
    0.59
    ς
    0.59
    THING
    0.56
     a
    0.55
    ات
    0.55
    ק
    0.54
    릭터
    0.54
     the
    0.53
    POSITIVE LOGITS
    ী
    0.53
    ية
    0.52
    をしている
    0.52
    を有する
    0.52
    を入れて
    0.50
    на
    0.49
    jenigen
    0.47
    quele
    0.46
    を発
    0.46
    を知
    0.46
    Activations Density 0.638%

    No Known Activations