© 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. 25931
    Prev
    Next
    INDEX
    Explanations

    collocations following common words

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

    Sidebar, popularity, multiplication

    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
     varía
    0.42
     utilizados
    0.42
     „
    0.42
     verdes
    0.40
     mahi
    0.40
     cream
    0.40
    >/</
    0.40
    atórios
    0.40
     atractivo
    0.40
    >
    0.40
    POSITIVE LOGITS
    ဏ
    0.41
    URUK
    0.41
     downregulation
    0.41
    预防
    0.40
    ่
    0.40
    ICAS
    0.39
    靠近
    0.39
    ADIAN
    0.36
    这里
    0.36
     hindered
    0.36
    Activations Density 0.000%

    No Known Activations