© 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. 199598
    Prev
    Next
    INDEX
    Explanations

    successful referral

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

    structured text elements

    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
    $:
    0.48
     contrived
    0.45
    ើន
    0.44
    ARTI
    0.42
     गंदगी
    0.42
    Intelligence
    0.41
    orul
    0.41
    ulsions
    0.41
    intelligence
    0.41
    碧
    0.41
    POSITIVE LOGITS
     groupBox
    0.48
     osim
    0.48
     tisu
    0.46
     sepat
    0.46
     membahas
    0.46
     suku
    0.46
     unidades
    0.43
     kuid
    0.43
     nisk
    0.43
     Nieder
    0.43
    Activations Density 0.000%

    No Known Activations