© 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. 31-GEMMASCOPE-2-RES-65K
    7. 8455
    Prev
    Next
    INDEX
    Explanations

    token security and planning

    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_31_width_65k_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
     شدید
    0.61
     മൂല
    0.57
     効果
    0.57
     የ
    0.54
     अथवा
    0.54
     інформа
    0.53
     teria
    0.53
    あるいは
    0.52
     យើង
    0.52
     અથવા
    0.52
    POSITIVE LOGITS
    L
    0.47
     fry
    0.46
    Bone
    0.46
    I
    0.43
    O
    0.43
    bond
    0.42
    roll
    0.42
     bond
    0.42
    Duck
    0.42
     task
    0.41
    Activations Density 0.014%

    No Known Activations