© 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. 160538
    Prev
    Next
    INDEX
    Explanations

    time of this writing

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

    imagine, immediately, like

    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
     measurements
    0.45
     tv
    0.45
     vụ
    0.44
    考
    0.44
    Asp
    0.44
    縈
    0.42
     in
    0.42
    ابق
    0.42
     commitments
    0.42
     mr
    0.41
    POSITIVE LOGITS
    relax
    0.47
     различи
    0.46
    kanie
    0.46
    rocchia
    0.45
     строение
    0.45
    templatemo
    0.45
     пе
    0.44
    editing
    0.44
    rune
    0.44
    e
    0.44
    Activations Density 0.000%

    No Known Activations