© 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. 204264
    Prev
    Next
    INDEX
    Explanations

    legal and ethical considerations

    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
     ဖြစ်
    0.54
     அல்ல
    0.51
     serão
    0.51
    𝒓
    0.49
     estão
    0.47
    𐰼
    0.47
    abhut
    0.47
    筈
    0.46
    ⋘
    0.46
    َد
    0.45
    POSITIVE LOGITS
    C
    0.53
    Y
    0.51
    _
    0.50
    c
    0.50
    in
    0.49
    W
    0.48
    E
    0.47
    m
    0.47
    y
    0.47
    V
    0.46
    Activations Density 0.001%

    No Known Activations