© 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. 11265
    Prev
    Next
    INDEX
    Explanations

    safety, security, monkeys, REM

    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
    ιασ
    2.15
    ikala
    2.14
    جم
    2.13
    /***/
    2.11
    𝗆
    2.09
    𝗁
    2.06
    ти
    2.06
    getCamera
    2.05
    ﾑ
    2.05
    schnitt
    2.04
    POSITIVE LOGITS
     得
    2.61
    lift
    2.53
     linguaggio
    2.43
    粵
    2.34
     lenguaje
    2.33
    倣
    2.33
     lèvres
    2.32
    tapping
    2.32
     gauze
    2.26
    ুহ
    2.24
    Activations Density 0.011%

    No Known Activations