© 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. 138672
    Prev
    Next
    INDEX
    Explanations

    financial and technical contexts

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

    physically crush, Claude 3 Opus, Old Man Tiber

    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
    ronique
    0.50
     নগ
    0.50
     niem
    0.48
    <unused18>
    0.48
    াদেশিক
    0.48
    🎱
    0.47
     নৌ
    0.47
     Hafen
    0.46
     Frédéric
    0.45
    }&=
    0.45
    POSITIVE LOGITS
    ع
    0.61
    هم
    0.59
    ست
    0.52
    ق
    0.50
    b
    0.48
    ش
    0.48
    د
    0.48
    ॢ
    0.47
    ພວກເຮົາ
    0.46
    أ
    0.46
    Activations Density 0.001%

    No Known Activations