© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 202473
    Prev
    Next
    INDEX
    Explanations

    plan

    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
     seabed
    0.47
    تك
    0.46
     précie
    0.46
    </a>
    0.45
     nombreux
    0.45
     naveg
    0.45
     ≠
    0.44
     richest
    0.44
    }}$
    0.44
     ν
    0.44
    POSITIVE LOGITS
    al
    0.57
    lt
    0.56
    ps
    0.55
    alta
    0.55
    ou
    0.54
    les
    0.54
    plan
    0.54
    classic
    0.53
    ne
    0.53
    fila
    0.53
    Activations Density 0.000%

    No Known Activations