© 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. 10630
    Prev
    Next
    INDEX
    Explanations

    sharing privacy

    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
    eaa
    2.64
    e
    2.62
    ordinate
    2.42
    eo
    2.37
    쩜
    2.37
     கொண்டிருக்கும்
    2.35
    ुद्ध
    2.34
    ようになりました
    2.29
     impress
    2.26
    eing
    2.24
    POSITIVE LOGITS
     pyt
    2.93
    𝓮
    2.89
    Zag
    2.79
    θυν
    2.78
    <bos>
    2.75
    isjon
    2.71
    iovas
    2.63
    ził
    2.62
    ovost
    2.61
    ιουργ
    2.60
    Activations Density 0.016%

    No Known Activations