© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 53761
    Prev
    Next
    INDEX
    Explanations

    roles and state, arrest

    np_acts-logits-general · gemini-2.5-flash-lite

    historical, biological, and emotional states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    CCc
    0.61
     chc
    0.53
    CCCCC
    0.51
    /}{
    0.51
    "#
    0.51
     Chavan
    0.50
     wspól
    0.48
    MORDOR
    0.48
    𝗰
    0.48
    CA
    0.48
    POSITIVE LOGITS
     barometer
    0.44
    ानी
    0.43
     ఆర్
    0.42
     ഏക
    0.42
    elor
    0.42
     گرفتار
    0.42
     useRouter
    0.41
     useEffect
    0.41
     ৩০
    0.41
    urilor
    0.41
    Activations Density 0.000%

    No Known Activations