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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13500
    Prev
    Next
    INDEX
    Explanations

    k/K/Kn/Kc/kem

    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_16k_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
    hz
    0.56
    t
    0.53
    h
    0.53
    IVE
    0.52
     Caz
    0.51
    n
    0.51
    ്ര
    0.51
    g
    0.50
    nq
    0.49
    y
    0.48
    POSITIVE LOGITS
     k
    0.66
     K
    0.66
    K
    0.63
     Klub
    0.62
     on
    0.58
    need
    0.57
    metic
    0.57
     половине
    0.56
     KI
    0.55
    rifft
    0.55
    Activations Density 0.802%

    No Known Activations