© 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. 219072
    Prev
    Next
    INDEX
    Explanations

    says that

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

    describes a concept

    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
    льнай
    0.54
    рано
    0.52
    自分で
    0.49
    有害
    0.48
    gifs
    0.47
    納税
    0.47
     pancre
    0.47
    ㌔
    0.47
     дума
    0.47
     évident
    0.46
    POSITIVE LOGITS
    }];
    0.50
    0.48
     Sprachen
    0.47
    }
    0.47
     Recognition
    0.47
    achter
    0.47
     Boundary
    0.44
     Bewegung
    0.44
     Nanjing
    0.44
     spezial
    0.43
    Activations Density 0.010%

    No Known Activations