© 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. 225949
    Prev
    Next
    INDEX
    Explanations

    our use, as well, alumni and

    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
    ↵
    0.55
     جر
    0.41
     propósito
    0.41
    ع
    0.41
     inversa
    0.40
     Kullan
    0.40
     Rhein
    0.39
     inaugural
    0.38
    ڈ
    0.37
    in
    0.37
    POSITIVE LOGITS
     mirip
    0.42
    苧
    0.42
    ἷ
    0.42
     hairdry
    0.42
    Calcium
    0.41
    素晴
    0.41
     montrent
    0.40
     onions
    0.40
    visiae
    0.40
    Semif
    0.40
    Activations Density 1.145%

    No Known Activations