© 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. 67095
    Prev
    Next
    INDEX
    Explanations

    make cleanup easy

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

    grave consequences

    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
    amacare
    0.49
    掄
    0.47
    診療
    0.46
    ನ್ನ
    0.46
    깃
    0.45
    гласно
    0.45
    रिक
    0.44
    पचारिक
    0.43
    ập
    0.42
    Referring
    0.42
    POSITIVE LOGITS
     t
    0.55
     φ
    0.51
     capitalize
    0.51
    aqua
    0.50
     UP
    0.49
     del
    0.49
     Bridge
    0.49
     BRIDGE
    0.49
     el
    0.48
     bridge
    0.48
    Activations Density 0.001%

    No Known Activations