© 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. 91690
    Prev
    Next
    INDEX
    Explanations

    noun followed by modifier

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

    animal names, characters

    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
     trimmer
    0.48
    $).
    0.47
    nfasis
    0.47
     tropos
    0.46
    iri
    0.45
    aitement
    0.44
    ྛ
    0.44
    ungsseite
    0.43
    cheid
    0.43
    +")
    0.43
    POSITIVE LOGITS
     hesitate
    0.47
     оправ
    0.46
    ват
    0.46
    数量
    0.46
    c
    0.45
     психо
    0.45
    begin
    0.44
    的选择
    0.44
     все
    0.44
     âge
    0.44
    Activations Density 0.001%

    No Known Activations