© 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. 3136
    Prev
    Next
    INDEX
    Explanations

    to followed by verb

    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
    eg
    1.26
    playback
    1.23
    resent
    1.21
    '
    1.19
    ear
    1.18
    residential
    1.18
    !--
    1.13
    ting
    1.13
     nearest
    1.13
    arket
    1.12
    POSITIVE LOGITS
    ים
    2.27
    ا۔
    2.23
    র
    2.19
    هه
    2.18
    <unused1230>
    2.07
     getNodeId
    2.06
    ের
    2.04
    𝒆
    2.04
    ം
    2.04
    ੀ
    2.01
    Activations Density 0.127%

    No Known Activations