© 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. 249365
    Prev
    Next
    INDEX
    Explanations

    Entertainment Weekly, HERE, So, YellowPages

    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
    óri
    0.56
    эй
    0.50
    ቁ
    0.50
     irregularities
    0.46
    امة
    0.46
     budú
    0.46
    ية
    0.45
    ны
    0.45
    ين
    0.45
    ты
    0.45
    POSITIVE LOGITS
    indic
    0.49
     OutputStream
    0.48
    background
    0.47
    }
    0.47
    bg
    0.46
    getLogger
    0.46
     갔
    0.46
    scrollTo
    0.46
    invalid
    0.46
    InputStream
    0.45
    Activations Density 0.002%

    No Known Activations