© 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. 149264
    Prev
    Next
    INDEX
    Explanations

    over 100 students

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

    screenplay scene headings

    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
    м
    0.54
    ILO
    0.51
    CENT
    0.50
    cento
    0.46
    CHEMICAL
    0.45
    blum
    0.45
     زن
    0.45
    ריך
    0.45
    焊
    0.45
    ILERS
    0.44
    POSITIVE LOGITS
     parked
    0.48
     vào
    0.45
    车
    0.45
     boarded
    0.44
     reigning
    0.44
     streets
    0.43
    ígen
    0.42
     Gym
    0.42
     góc
    0.41
    学员
    0.41
    Activations Density 0.001%

    No Known Activations