© 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. 173768
    Prev
    Next
    INDEX
    Explanations

    adolescents toddlers mapping Saul broke find that young

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

    multimodal capabilities, best levers

    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
     लष्
    0.52
     मानक
    0.50
    EPT
    0.48
    蝠
    0.48
     sauté
    0.48
    uillez
    0.47
     न्यायालया
    0.47
     ベージュ
    0.47
    XO
    0.47
     UIColor
    0.46
    POSITIVE LOGITS
    in
    0.47
    inę
    0.43
    
    0.43
     revolved
    0.42
     Sams
    0.41
    دين
    0.41
    غیر
    0.41
    قي
    0.40
     strange
    0.40
    וס
    0.40
    Activations Density 0.000%

    No Known Activations