© 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
    2. Gemma-3-27B-IT
    3. 53-GEMMASCOPE-2-RES-262K
    4. 4379
    Prev
    Next
    INDEX
    Explanations

    terms of service

    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_53_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
    Role
    0.38
    孬
    0.37
     Role
    0.36
    Sense
    0.36
     ações
    0.36
    role
    0.36
    moves
    0.36
     Matters
    0.36
     TECHNIQUES
    0.35
    ⬝
    0.35
    POSITIVE LOGITS
     attack
    0.53
     operation
    0.47
     play
    0.46
     inquiry
    0.43
     conscience
    0.42
     contention
    0.42
     lading
    0.41
     reference
    0.41
     ownership
    0.40
     difficulty
    0.40
    Activations Density 0.085%

    No Known Activations