© 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. 179430
    Prev
    Next
    INDEX
    Explanations

    in the sidebar

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

    area. height. intensity. discharge. curve

    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
    EQU
    0.52
    Otra
    0.52
    L
    0.52
     voork
    0.48
     otra
    0.48
    T
    0.48
    AL
    0.47
    하라
    0.47
    nél
    0.47
    K
    0.47
    POSITIVE LOGITS
     integrative
    0.50
     intensity
    0.47
     broadcasts
    0.46
     kHz
    0.45
     undetectable
    0.44
     apostles
    0.43
     toll
    0.43
     abrasive
    0.43
     enrolled
    0.42
     eukaryotes
    0.42
    Activations Density 0.000%

    No Known Activations