© 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. 76853
    Prev
    Next
    INDEX
    Explanations

    showing signs or conditions

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

    word sequences leading to specific phrases

    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
     cladding
    0.51
     gasket
    0.50
     staple
    0.47
     môn
    0.46
     fragile
    0.46
    হ
    0.44
     rejection
    0.43
     lamps
    0.43
     sterile
    0.43
     passable
    0.42
    POSITIVE LOGITS
    <unused1821>
    0.54
    avait
    0.48
     चुका
    0.46
    كتر
    0.46
    intégr
    0.45
    หวาน
    0.45
     führte
    0.44
     自分
    0.44
    <unused774>
    0.43
    苌
    0.43
    Activations Density 0.000%

    No Known Activations