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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 14168
    Prev
    Next
    INDEX
    Explanations

    free tier purchasing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
    matical
    2.84
    oretum
    2.78
     Meridian
    2.77
    ども
    2.71
    бора
    2.70
     শতকরা
    2.68
    وطه
    2.66
    濂
    2.65
     polynomials
    2.61
    cracker
    2.55
    POSITIVE LOGITS
    ide
    2.74
    iper
    2.59
    ી
    2.55
    eff
    2.41
    isance
    2.41
    hit
    2.35
    es
    2.34
    a
    2.29
    engagement
    2.29
    jetbrains
    2.29
    Activations Density 0.000%

    No Known Activations