© 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. 193707
    Prev
    Next
    INDEX
    Explanations

    word combinations

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

    disclaimers and hypothetical scenarios

    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
    ୍ର
    0.50
    ➊
    0.46
    োই
    0.42
     grew
    0.42
    ર્ટ
    0.42
    ʐ
    0.41
    /#{
    0.40
    шон
    0.40
     গেছে
    0.40
    ូន
    0.39
    POSITIVE LOGITS
    และ
    0.46
    อีก
    0.44
     Spar
    0.43
     emas
    0.42
    éto
    0.41
     Scotty
    0.41
    😷
    0.41
    Relations
    0.40
    0.40
    </i>
    0.40
    Activations Density 0.000%

    No Known Activations