© 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. 202374
    Prev
    Next
    INDEX
    Explanations

    officials found, want to

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

    focus on observation or avoidance

    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
     Dal
    0.48
     সদা
    0.46
     Peas
    0.45
     मातृ
    0.44
    ORICAL
    0.43
    athy
    0.42
     Beneath
    0.42
    y
    0.42
     Achilles
    0.42
     minim
    0.41
    POSITIVE LOGITS
    NATO
    0.50
     militari
    0.46
     dég
    0.45
    سبة
    0.45
     dryer
    0.45
    捪
    0.45
    $,
    0.45
     réseau
    0.45
    "]]
    0.45
     militare
    0.45
    Activations Density 0.000%

    No Known Activations