© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 12320
    Prev
    Next
    INDEX
    Explanations

    relative pronouns or possessives

    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
    is
    0.56
     footprint
    0.50
    on
    0.45
    in
    0.44
     footprints
    0.44
    ையை
    0.43
    X
    0.43
    <img>
    0.43
    =
    0.43
    ing
    0.42
    POSITIVE LOGITS
     whom
    0.55
     الذين
    0.55
     Whom
    0.50
     जिनकी
    0.47
     हत्याकांड
    0.47
     wszel
    0.46
    是谁
    0.46
     whose
    0.46
     كلهم
    0.44
     cuyos
    0.43
    Activations Density 0.066%

    No Known Activations