© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 23450
    Prev
    Next
    INDEX
    Explanations

    unique

    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
    G
    0.64
    T
    0.61
    K
    0.61
    ka
    0.56
    M
    0.55
    N
    0.55
    O
    0.55
    F
    0.54
    S
    0.52
    C
    0.52
    POSITIVE LOGITS
     për
    0.50
    для
    0.47
    वियस
    0.46
    ୬
    0.45
     দাড়
    0.43
     ऑफिसियल
    0.42
    emento
    0.42
     Comer
    0.41
     для
    0.41
     pentru
    0.41
    Activations Density 0.011%

    No Known Activations