© 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. 227602
    Prev
    Next
    INDEX
    Explanations

    new images for you

    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
    ബൈ
    0.46
     amici
    0.43
    风
    0.42
    ब
    0.42
     rapper
    0.41
    东
    0.41
    俺
    0.41
     runners
    0.41
     boyhood
    0.41
     occhi
    0.40
    POSITIVE LOGITS
    Recipient
    0.44
     －
    0.42
    сиз
    0.42
    ('',
    0.42
    ContextProvider
    0.42
     Tann
    0.42
     deducting
    0.42
    ер
    0.41
    Preference
    0.41
     Recipients
    0.41
    Activations Density 0.001%

    No Known Activations