© 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. 160512
    Prev
    Next
    INDEX
    Explanations

    on-line analytical processing

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

    account folders

    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
    ╩
    0.47
    वाला
    0.45
    صیٰ
    0.45
    ƒ
    0.45
     Modern
    0.44
    icrous
    0.44
    獎
    0.44
     registrar
    0.43
    õe
    0.43
    y
    0.42
    POSITIVE LOGITS
     לצ
    0.52
     Monteiro
    0.47
     Сасик
    0.47
    TypeText
    0.46
    phenol
    0.45
     পুলিশ
    0.45
     anisotropy
    0.44
     reappear
    0.44
     desaparecido
    0.44
     Са
    0.44
    Activations Density 0.001%

    No Known Activations