© 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. 164779
    Prev
    Next
    INDEX
    Explanations

    architectural, next year, cake, breath

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

    programming constructs, personal, client

    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
     hObject
    0.44
    ు
    0.42
    aked
    0.41
    юро
    0.40
    стал
    0.40
    很容易
    0.39
    也能
    0.39
    很快
    0.39
    保
    0.39
    amily
    0.38
    POSITIVE LOGITS
     prévention
    0.54
     și
    0.50
     orthopedic
    0.50
     супру
    0.49
     מפ
    0.48
     obsług
    0.48
     architectural
    0.47
     nourriture
    0.47
     Dialer
    0.46
     zuz
    0.46
    Activations Density 0.000%

    No Known Activations