© 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. 101780
    Prev
    Next
    INDEX
    Explanations

    gathering information

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

    asking for more details

    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
     なん
    0.56
     அவர்கள்
    0.53
     आधिकारिक
    0.53
     निजामा
    0.52
     इन्हें
    0.51
    จำนวน
    0.51
    רי
    0.51
     {}>,
    0.51
     Procur
    0.50
     произво
    0.50
    POSITIVE LOGITS
    on
    0.52
    o
    0.47
    atoire
    0.44
    ResponseEntity
    0.44
    ety
    0.42
    intermediates
    0.42
    ويم
    0.41
    annotation
    0.41
    仪
    0.41
    ilane
    0.40
    Activations Density 0.001%

    No Known Activations