© 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. 79716
    Prev
    Next
    INDEX
    Explanations

    state followed by describing word

    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
     مليار
    0.56
    Ⴖ
    0.53
    等人
    0.52
    Beth
    0.51
     கூட்டணி
    0.51
     واع
    0.51
    𝓻
    0.51
    <unused968>
    0.50
    Tribune
    0.50
    Ⴌ
    0.49
    POSITIVE LOGITS
    in
    0.49
     desk
    0.45
     per
    0.44
    are
    0.43
     ceased
    0.43
    0
    0.43
    op
    0.42
     perme
    0.41
     real
    0.41
    NUMX
    0.41
    Activations Density 0.007%

    No Known Activations