© 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. 193677
    Prev
    Next
    INDEX
    Explanations

    parts of category beds bill

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

    petite, Tall, Box, interfaces, water

    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
    INY
    0.52
    Escolhido
    0.52
    Depart
    0.50
    Look
    0.50
    ㄆ
    0.50
    仂
    0.49
    Somebody
    0.49
    彭
    0.48
    শকার
    0.48
    DistanceFrom
    0.47
    POSITIVE LOGITS
     ist
    0.48
    am
    0.47
     čini
    0.45
    ak
    0.45
    ug
    0.44
    ah
    0.43
     interested
    0.43
     l
    0.43
     nhất
    0.42
    rh
    0.42
    Activations Density 0.000%

    No Known Activations