© 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. 125553
    Prev
    Next
    INDEX
    Explanations

    demonstrates and certainly

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

    overall framework

    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
    ಂತ್ರ
    0.49
    чи
    0.48
    ARCH
    0.46
    沆
    0.46
    BER
    0.46
    aplic
    0.45
    imetable
    0.44
    وك
    0.44
    inicio
    0.44
    ेंट
    0.44
    POSITIVE LOGITS
     Starring
    0.55
     InputAction
    0.54
     Phone
    0.50
     Myanmar
    0.50
     江
    0.50
     Name
    0.49
     Created
    0.49
     Club
    0.48
    ]))
    0.47
     dSample
    0.46
    Activations Density 0.000%

    No Known Activations