© 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. 60839
    Prev
    Next
    INDEX
    Explanations

    instructions and links

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

    states and conditions

    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
     निः
    0.45
     inmates
    0.44
    ྐ
    0.44
     skle
    0.44
     sighs
    0.43
    コツ
    0.42
     ት
    0.42
    varrho
    0.42
     locals
    0.41
     delicacies
    0.41
    POSITIVE LOGITS
    颁
    0.45
    鳍
    0.44
     препо
    0.43
    メリカ
    0.43
     potenz
    0.42
    ır
    0.42
    étion
    0.41
    Discipl
    0.41
    还会
    0.41
     cominc
    0.41
    Activations Density 0.000%

    No Known Activations