© 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. 16-GEMMASCOPE-2-RES-262K
    7. 3579
    Prev
    Next
    INDEX
    Explanations

    numbered centuries

    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_16_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
    i
    0.36
    اک
    0.32
    5
    0.32
    .
    0.31
    2
    0.31
     l
    0.31
    ö
    0.30
    ica
    0.29
    iel
    0.29
    US
    0.29
    POSITIVE LOGITS
    t
    0.38
    ్రియ
    0.33
    у
    0.31
     భాగ
    0.30
     jedem
    0.30
    ش
    0.30
     unload
    0.29
    ন
    0.29
     exclude
    0.29
    риал
    0.29
    Activations Density 0.028%

    No Known Activations