© 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. 208163
    Prev
    Next
    INDEX
    Explanations

    locality info

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

    username and password

    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
    मूल
    0.51
     आड
    0.47
    ovány
    0.46
     पोहो
    0.46
    畢
    0.46
    कुछ
    0.45
     менее
    0.44
     ужа
    0.44
     başka
    0.44
     Испании
    0.44
    POSITIVE LOGITS
     @
    0.46
     paradoxical
    0.44
     repo
    0.43
     conceded
    0.43
     corresponding
    0.43
     concession
    0.43
     customer
    0.43
     severity
    0.42
     consisting
    0.42
     oneness
    0.42
    Activations Density 0.000%

    No Known Activations