© 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. 196990
    Prev
    Next
    INDEX
    Explanations

    behind someone, mobile frequency

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

    telling versus showing

    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
    issued
    0.49
     কূটনীতিক
    0.49
     નક્
    0.48
    rowning
    0.46
     Carleton
    0.45
    orec
    0.45
    }{{
    0.45
    nun
    0.45
    entity
    0.44
    unlink
    0.44
    POSITIVE LOGITS
     lamb
    0.47
     समाज
    0.43
    اجة
    0.42
    ζο
    0.42
    ີ
    0.41
    Lamb
    0.41
     condo
    0.40
    लीस
    0.40
    
    0.39
     bourgeois
    0.38
    Activations Density 0.000%

    No Known Activations