© 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. 107187
    Prev
    Next
    INDEX
    Explanations

    moon was

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

    code and logic components

    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
     மர
    0.46
    UserData
    0.45
    楤
    0.45
    园
    0.44
    Wer
    0.44
     मैन
    0.44
     BUILDING
    0.43
    ParentElement
    0.43
    新能源
    0.43
    括
    0.42
    POSITIVE LOGITS
     yeux
    0.47
     denials
    0.47
     oxford
    0.46
    headed
    0.46
     hotel
    0.45
     assurances
    0.44
    ल्फी
    0.43
     tendered
    0.43
     maisons
    0.43
     precondition
    0.42
    Activations Density 0.001%

    No Known Activations