© 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. 106045
    Prev
    Next
    INDEX
    Explanations

    getting / writing / telling

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

    questions and definitions

    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
    9
    0.47
     માર
    0.46
     auftreten
    0.46
    ilt
    0.44
     limitation
    0.44
     bior
    0.44
     klicken
    0.42
     टीस्पून
    0.41
     hospitalization
    0.41
     limitations
    0.41
    POSITIVE LOGITS
    jol
    0.45
     Gaw
    0.43
    𝙖
    0.43
    знав
    0.42
     Madre
    0.41
     Aruba
    0.41
    कारक
    0.41
    čných
    0.41
     Alias
    0.41
    њ
    0.41
    Activations Density 0.000%

    No Known Activations