© 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. 62492
    Prev
    Next
    INDEX
    Explanations

    My Fair Lady, Doolittle, eliminate frizz

    np_acts-logits-general · gemini-2.5-flash-lite

    common phrases and collocations

    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
     patrimoine
    0.42
    projectId
    0.42
     constitutive
    0.40
     नती
    0.39
    postId
    0.39
    詈
    0.39
    indexOf
    0.39
    媜
    0.38
    岕
    0.38
     relational
    0.38
    POSITIVE LOGITS
    REX
    0.49
     sostiene
    0.45
     drogas
    0.45
     avrà
    0.44
     engineered
    0.44
    RA
    0.42
    嘶
    0.41
     RX
    0.41
     คว
    0.41
    ABE
    0.40
    Activations Density 0.000%

    No Known Activations