© 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
    2. Gemma-3-270M
    3. 12-GEMMASCOPE-2-RES-16K
    4. 6014
    Prev
    Next
    INDEX
    Explanations

    html input type and option value

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-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
    قا
    1.90
    зін
    1.84
    голо
    1.81
    ža
    1.79
    гка
    1.76
    ranno
    1.74
    кто
    1.73
    ">&#
    1.72
    ">–
    1.71
     пусто
    1.71
    POSITIVE LOGITS
    (|
    1.46
    ("#{
    1.44
    ((
    1.36
    (*
    1.30
     (~
    1.29
     trajets
    1.26
    (
    1.24
    IDAE
    1.22
    ≪
    1.22
    ((*
    1.19
    Activations Density 0.000%

    No Known Activations