© 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. 4951
    Prev
    Next
    INDEX
    Explanations

    specific techniques

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

    learning skills and activities

    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
    system
    0.32
    erreur
    0.31
    amburger
    0.31
     spongy
    0.30
    ಬ್
    0.30
    nemonic
    0.27
    뀔
    0.27
    摘要
    0.27
     cryptographic
    0.27
    snapshot
    0.27
    POSITIVE LOGITS
     bootcamp
    0.35
    /
    0.35
     Techniques
    0.35
    -
    0.33
     tại
    0.33
     Bootcamp
    0.32
     extraordinaire
    0.32
    खोरी
    0.32
     at
    0.32
    ,
    0.32
    Activations Density 0.570%

    No Known Activations