© 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. 155138
    Prev
    Next
    INDEX
    Explanations

    financial and project details

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

    enhanced or offered benefits

    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
     hab
    0.52
     happening
    0.50
     polluting
    0.50
    hab
    0.46
     Hab
    0.46
     Lent
    0.45
     L
    0.45
     galactic
    0.44
    }\{\
    0.44
     convention
    0.44
    POSITIVE LOGITS
    KeyCode
    0.48
     дисципли
    0.48
     если
    0.48
     soziale
    0.47
    Seb
    0.46
    如果
    0.46
    Acetyl
    0.46
     matured
    0.45
    দান
    0.45
     ấn
    0.45
    Activations Density 0.000%

    No Known Activations