© 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. 144812
    Prev
    Next
    INDEX
    Explanations

    attorneys understand

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

    regulate mood, bare minimum, offers

    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
     tedy
    0.42
     sozial
    0.42
    ]
    0.41
     certiorari
    0.40
    れて
    0.40
     genomic
    0.40
    （
    0.39
     timestamp
    0.39
     Torre
    0.39
    つまり
    0.39
    POSITIVE LOGITS
    楸
    0.50
     минима
    0.48
     ấn
    0.48
    强势
    0.48
    及
    0.44
    陪伴
    0.43
     thấp
    0.43
     ngắn
    0.43
     interesados
    0.43
    ến
    0.42
    Activations Density 0.003%

    No Known Activations