© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11139
    Prev
    Next
    INDEX
    Explanations

    acquisition by

    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
     TIMESTAMP
    2.72
    eba
    2.68
    𝙩
    2.62
    tir
    2.60
    لاھ
    2.53
    チューブ
    2.52
    ጨማሪ
    2.48
    ಟರ್
    2.46
    𝙚
    2.42
    መሳሳይ
    2.42
    POSITIVE LOGITS
    ق
    2.44
     fällt
    2.25
    ળો
    2.02
    /−
    1.98
    ′
    1.97
     itemscope
    1.96
    ′,
    1.96
    role
    1.94
    CIO
    1.92
    ignac
    1.90
    Activations Density 0.004%

    No Known Activations