© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 1629
    Prev
    Next
    INDEX
    Explanations

    seasonal endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    s
    1.56
    nex
    1.54
    sf
    1.50
    ের
    1.46
    rac
    1.43
    nap
    1.40
    n
    1.39
    nok
    1.37
    sas
    1.37
    rong
    1.34
    POSITIVE LOGITS
    ً
    3.08
    anwhile
    2.81
    urope
    2.73
    volence
    2.59
    ffekt
    2.54
    chanical
    2.47
    cciones
    2.45
    ccionar
    2.44
    cción
    2.43
    hány
    2.42
    Activations Density 0.380%

    No Known Activations