© 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. 68613
    Prev
    Next
    INDEX
    Explanations

    indemnify harmless, dentistry Notes, quarterly on, caused by, weather forecast, hearing fee

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

    before full or after `begins`

    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
    ♂
    0.42
    ™
    0.40
     intercellular
    0.40
    ={`${
    0.39
     আট
    0.39
    檔案
    0.39
    শ্চর্য
    0.39
     interplay
    0.38
    観察
    0.38
     Learners
    0.38
    POSITIVE LOGITS
    izante
    0.48
     zgodnie
    0.47
    фы
    0.46
     oppure
    0.45
     garnished
    0.44
     는
    0.44
     owed
    0.43
     determinante
    0.43
     conformément
    0.43
    đe
    0.42
    Activations Density 0.003%

    No Known Activations