© 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. 42588
    Prev
    Next
    INDEX
    Explanations

    back unto

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

    conditional phrases or clauses

    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
    ሪክ
    0.53
     નામ
    0.50
     preventiva
    0.48
     विल
    0.46
     buscan
    0.46
    ْ
    0.45
     작
    0.45
    孤
    0.45
    riften
    0.44
     هغه
    0.44
    POSITIVE LOGITS
    (
    0.50
     Site
    0.44
    Studio
    0.43
    但是
    0.43
    வரும்
    0.43
     as
    0.43
     Studio
    0.42
    Flying
    0.42
    ...(
    0.42
    Site
    0.42
    Activations Density 0.000%

    No Known Activations