© 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. 126688
    Prev
    Next
    INDEX
    Explanations

    specific informational content

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

    specifically listed

    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
    Partners
    0.45
    ણ
    0.45
    Buddy
    0.44
     Second
    0.44
     Harvard
    0.44
    Parse
    0.44
     Partners
    0.43
     در
    0.43
    άν
    0.43
    搁
    0.43
    POSITIVE LOGITS
     materias
    0.47
     qubits
    0.44
    verlag
    0.44
    iser
    0.44
     conclusions
    0.43
     fileobj
    0.43
     treaties
    0.42
     memos
    0.42
     alkaloids
    0.41
    ]=(
    0.41
    Activations Density 0.001%

    No Known Activations