© 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. 184725
    Prev
    Next
    INDEX
    Explanations

    online booking

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

    agency, agents, system turn

    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
    携
    0.51
    蚬
    0.48
    確実に
    0.46
    宻
    0.46
     equatorial
    0.44
     searchQuery
    0.44
    TextureData
    0.44
    瀾
    0.44
    渡し
    0.43
     titan
    0.43
    POSITIVE LOGITS
    7
    0.57
    6
    0.57
    adt
    0.52
    4
    0.52
    5
    0.52
    apt
    0.51
    vrage
    0.51
    3
    0.51
    ulp
    0.49
    adh
    0.49
    Activations Density 0.000%

    No Known Activations