© 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. 3148
    Prev
    Next
    INDEX
    Explanations

    tool and related phrase

    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
    的
    2.71
    ations
    2.65
    ס
    2.58
    ities
    2.58
    с
    2.54
    的上
    2.53
    iterations
    2.49
    то
    2.49
    athermy
    2.49
    ます
    2.48
    POSITIVE LOGITS
    ه
    3.86
    ా
    3.51
    ので
    3.38
    ein
    3.33
    eah
    3.26
    e
    3.23
    هي
    3.17
    ে
    3.15
    ele
    3.12
    ojs
    3.10
    Activations Density 0.082%

    No Known Activations