© 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. 197484
    Prev
    Next
    INDEX
    Explanations

    offers and purchases

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

    here followed by confirmation

    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
     Gazprom
    0.50
     நிச்ச
    0.49
    ніза
    0.48
    紜
    0.48
    垨
    0.48
    пус
    0.47
    ходя
    0.47
    cipl
    0.46
    сій
    0.46
    рес
    0.46
    POSITIVE LOGITS
     betekent
    0.43
     serine
    0.43
    iselle
    0.42
     glycine
    0.42
     compliqué
    0.41
    <0x8C>
    0.41
     permite
    0.41
    haha
    0.40
    alle
    0.40
    Details
    0.40
    Activations Density 0.001%

    No Known Activations