© 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. 236624
    Prev
    Next
    INDEX
    Explanations

    tender, workers, class, creators

    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
    😴
    0.52
     Deng
    0.50
    式の
    0.49
    茠
    0.48
     implying
    0.47
     জড়িত
    0.47
     pumping
    0.47
     sickening
    0.47
    มาก
    0.46
     Conditioning
    0.46
    POSITIVE LOGITS
    ὦ
    0.54
    骓
    0.44
    jm
    0.43
    ειο
    0.43
    cz
    0.42
    怒
    0.42
    gypte
    0.42
    뤽
    0.42
    ForeignKey
    0.41
    橼
    0.41
    Activations Density 0.000%

    No Known Activations