© 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. 88004
    Prev
    Next
    INDEX
    Explanations

    marvelous work and wonder

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

    birds, crows, and animals

    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
    ᱗
    0.58
    に関しては
    0.53
     hypersur
    0.52
     sigurn
    0.52
     јо
    0.51
    んにちは
    0.50
     atteggi
    0.49
    ᄍ
    0.49
    डर
    0.48
    VERS
    0.48
    POSITIVE LOGITS
     inventory
    0.50
     guide
    0.48
    0.48
     r
    0.47
    ory
    0.46
     organizing
    0.46
     new
    0.46
     symmetry
    0.46
     plunder
    0.46
     seed
    0.45
    Activations Density 0.001%

    No Known Activations