© 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. 34102
    Prev
    Next
    INDEX
    Explanations

    not working or impossible

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

    less common or not recommended

    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
     Perspekt
    0.40
    orsz
    0.38
    夫婦
    0.38
    ⸝
    0.38
     tils
    0.37
    ندگان
    0.37
     zwar
    0.37
    ',)
    0.37
     brewing
    0.36
    hets
    0.36
    POSITIVE LOGITS
     MODERN
    0.50
     מע
    0.43
     această
    0.42
     कर्फ्यू
    0.41
     현대
    0.40
     эту
    0.40
    initpos
    0.40
     MUST
    0.39
    燔
    0.39
     சூரிய
    0.39
    Activations Density 0.008%

    No Known Activations