© 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. 40791
    Prev
    Next
    INDEX
    Explanations

    requires daily brushing

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

    need more or be sad

    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
     kucing
    0.49
    🐾
    0.47
    ডাক
    0.47
     zebrafish
    0.46
     feline
    0.46
     catamaran
    0.45
    closeup
    0.45
     blueberry
    0.45
    ificar
    0.44
     veterin
    0.44
    POSITIVE LOGITS
     ద్వ
    0.42
     Popul
    0.41
     ←
    0.41
    िरपेक्ष
    0.41
    紵
    0.41
     ബന്ധ
    0.40
     commutes
    0.40
     AGO
    0.40
     excused
    0.39
     academic
    0.39
    Activations Density 0.058%

    No Known Activations