© 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. 231844
    Prev
    Next
    INDEX
    Explanations

    add bindings, preached everywhere, Do you

    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
     (
    0.71
     Neste
    0.52
    *
    0.50
     halogen
    0.46
     Leu
    0.46
    <sup>
    0.46
    <i>
    0.45
     logo
    0.44
    篑
    0.44
     PSG
    0.43
    POSITIVE LOGITS
    timevals
    0.47
    serviceTime
    0.47
    retryWrites
    0.47
    ScreenBinding
    0.47
    airo
    0.46
    ର୍
    0.46
    thro
    0.45
     మార్
    0.45
    ור
    0.44
    Beans
    0.44
    Activations Density 0.001%

    No Known Activations