© 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. 81786
    Prev
    Next
    INDEX
    Explanations

    Mama, grandma, friend, Miss

    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
     there
    0.44
     там
    0.43
     и
    0.42
     >
    0.41
     did
    0.40
    રસ
    0.40
    rzez
    0.39
     had
    0.39
     සිය
    0.39
    가
    0.39
    POSITIVE LOGITS
    अच्छ
    0.51
     conducción
    0.43
    スケ
    0.42
    پيديا
    0.42
    તાવ
    0.41
    لاك
    0.41
    щины
    0.40
    вной
    0.40
     recovery
    0.40
    Doll
    0.40
    Activations Density 0.001%

    No Known Activations