© 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. 148762
    Prev
    Next
    INDEX
    Explanations

    insurance policy structure

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

    career exploration

    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
     to
    0.65
     Morris
    0.48
    }
    0.48
     Man
    0.46
     Williams
    0.46
     Evans
    0.45
     Roman
    0.45
     Ford
    0.45
     Brewers
    0.44
     breaker
    0.44
    POSITIVE LOGITS
    猝
    0.52
     кіль
    0.48
     organizz
    0.47
     disorganized
    0.47
     органі
    0.46
     조직
    0.46
     gestaltet
    0.46
     جامعه
    0.46
    uncak
    0.45
     організа
    0.45
    Activations Density 0.000%

    No Known Activations