© 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. 113622
    Prev
    Next
    INDEX
    Explanations

    entities and their states

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

    punctuation, separators, and abstract concepts

    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
    tty
    0.51
    љу
    0.50
    ју
    0.49
    enty
    0.47
    y
    0.46
     څ
    0.45
    lieder
    0.44
    IU
    0.43
    dete
    0.43
    ISTER
    0.42
    POSITIVE LOGITS
    سات
    0.45
     pagamento
    0.45
    έχ
    0.44
    直し
    0.43
     eût
    0.43
     alguém
    0.42
     enfin
    0.41
    áž
    0.41
     shaker
    0.41
    払
    0.41
    Activations Density 0.000%

    No Known Activations