© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 285
    Prev
    Next
    INDEX
    Explanations

    E followed by bola, 4, asi, rotic, clips

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    缡
    0.46
    ሖ
    0.45
    ৩৬
    0.44
    Przypisy
    0.43
    antlr
    0.41
    ◝
    0.41
    ಾಗ
    0.40
    dishwasher
    0.40
    atoms
    0.40
    رداری
    0.40
    POSITIVE LOGITS
     E
    1.02
     e
    0.84
    E
    0.66
    volving
    0.57
     eminent
    0.55
    fficacy
    0.52
    cellent
    0.49
     Eiffel
    0.49
     echelon
    0.49
     eerie
    0.47
    Activations Density 0.046%

    No Known Activations