© 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. 180098
    Prev
    Next
    INDEX
    Explanations

    imagina

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

    string manipulation and code

    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
    Negative Logits
    ẞ
    0.42
    ßen
    0.41
     роли
    0.40
     }\
    0.39
     философ
    0.39
     den
    0.38
     médaille
    0.38
    }_{-
    0.38
     سال
    0.38
     sy
    0.38
    POSITIVE LOGITS
     imagina
    0.42
    <unused78>
    0.42
    includ
    0.42
     Backyard
    0.42
     organi
    0.41
     backyard
    0.40
    meln
    0.39
     includ
    0.38
     快
    0.37
     काटकर
    0.37
    Activations Density 0.024%

    No Known Activations