© 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. 46308
    Prev
    Next
    INDEX
    Explanations

    global network

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

    creation and functionality

    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
     편리
    0.47
    AVLNode
    0.47
    stepToken
    0.47
    uels
    0.46
    ایش
    0.45
     ちゃう
    0.45
    inputFields
    0.45
    }}}-\
    0.45
     kuitenkin
    0.44
    InitTypeDef
    0.44
    POSITIVE LOGITS
     to
    0.50
     popularly
    0.48
     Moreno
    0.47
    甥
    0.44
     Mission
    0.44
     Ricci
    0.44
     sucede
    0.43
     Camacho
    0.43
     Consent
    0.43
     Possession
    0.43
    Activations Density 0.000%

    No Known Activations