© 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. 65146
    Prev
    Next
    INDEX
    Explanations

    defend against, collision in, the ability, leading edge

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

    overwhelming

    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
    d
    0.47
    Unh
    0.46
    د
    0.46
    褻
    0.45
    شه
    0.44
     होके
    0.44
    علام
    0.44
    сі
    0.44
    دخل
    0.43
    哎
    0.43
    POSITIVE LOGITS
     গলা
    0.47
     বন
    0.46
    ności
    0.46
     jit
    0.45
     সং
    0.45
    lebn
    0.45
    ochen
    0.44
    cton
    0.43
     দিলো
    0.43
     বলিল
    0.42
    Activations Density 0.000%

    No Known Activations