© 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. 109896
    Prev
    Next
    INDEX
    Explanations

    opens a new window or tab

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

    penetration, assignment, geometry, health, dates, openings

    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
     jeweiligen
    0.50
     enga
    0.48
    texts
    0.46
    ン
    0.45
     suces
    0.44
     respectivos
    0.43
     шаг
    0.42
    ]$.
    0.42
     صحیح
    0.41
     restos
    0.41
    POSITIVE LOGITS
    iennent
    0.48
     Bellevue
    0.47
    দৌ
    0.46
     którym
    0.45
     health
    0.45
    Health
    0.45
    쾨
    0.44
     demeanor
    0.44
    Retrieve
    0.44
    améliorer
    0.44
    Activations Density 0.000%

    No Known Activations