© 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. 143031
    Prev
    Next
    INDEX
    Explanations

    lists, published, December, identifier

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

    movement and actions

    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
    čen
    0.49
     있었다
    0.46
     เด็ก
    0.45
     halinde
    0.45
    `}
    0.45
     almacen
    0.43
    ख्
    0.43
     विनम्र
    0.43
     personne
    0.42
     अल्को
    0.42
    POSITIVE LOGITS
     Movement
    0.46
    Movement
    0.46
    ায়ত্ত
    0.44
    ﮐ
    0.44
    шение
    0.44
    സ്ഥാന
    0.43
    onation
    0.42
    চরণ
    0.42
    cą
    0.42
     songwriting
    0.41
    Activations Density 0.000%

    No Known Activations