© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 84012
    Prev
    Next
    INDEX
    Explanations

    causes, capabilities, fighting, downsides

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ဒ
    0.43
     également
    0.41
    }
    0.41
     अक्टूबर
    0.40
     građ
    0.40
     própria
    0.38
     aquellas
    0.38
     sebagian
    0.38
    当地
    0.38
     \&
    0.37
    POSITIVE LOGITS
     wheelchair
    0.48
    ొప్ప
    0.48
    ছাত্র
    0.45
    ຢູ່
    0.44
     уйнау
    0.42
    ulia
    0.41
    juana
    0.41
    ınar
    0.41
     backstage
    0.40
    Sean
    0.40
    Activations Density 0.031%

    No Known Activations