© 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. 16-GEMMASCOPE-2-RES-262K
    7. 48041
    Prev
    Next
    INDEX
    Explanations

    or so followed by pronouns

    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
    ARI
    0.55
    Ā
    0.50
    ANTE
    0.48
     Tsun
    0.48
     Ll
    0.48
     aunts
    0.48
    kA
    0.48
    ynia
    0.48
    曛
    0.47
    ->"
    0.47
    POSITIVE LOGITS
    according
    0.70
    ר
    0.70
    er
    0.68
    in
    0.66
    ة
    0.64
     volgens
    0.61
    ат
    0.60
     dle
    0.60
    る
    0.59
     σύμφωνα
    0.59
    Activations Density 0.000%

    No Known Activations