© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 76156
    Prev
    Next
    INDEX
    Explanations

    numeric sequences followed by 1

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

    temperature, angle, or exponent

    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
     দুটি
    0.44
     modelos
    0.44
     দুইটি
    0.42
     regole
    0.41
    मॉडल
    0.40
    בק
    0.40
    બે
    0.39
    '}}>
    0.39
     geometries
    0.39
     gehabt
    0.38
    POSITIVE LOGITS
     multicellular
    0.40
     azi
    0.38
    zsche
    0.38
     carbox
    0.37
     coarsely
    0.37
     somebody
    0.36
     psychosocial
    0.36
     vibhav
    0.35
     collectively
    0.35
     bor
    0.35
    Activations Density 0.004%

    No Known Activations