© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 244455
    Prev
    Next
    INDEX
    Explanations

    possessive pronoun/conjunction/preposition + noun/verb/adverb/article

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SH
    0.52
    記
    0.52
    RI
    0.49
    涓
    0.48
    一
    0.48
    Uses
    0.48
    MC
    0.47
    前
    0.47
    January
    0.46
    टिया
    0.46
    POSITIVE LOGITS
     obraz
    0.51
     dérou
    0.51
     CID
    0.51
     poesia
    0.50
     concent
    0.50
    ட்டும்
    0.49
     gid
    0.49
     procurar
    0.49
     universitario
    0.48
     искать
    0.48
    Activations Density 0.000%

    No Known Activations