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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 8680
    Prev
    Next
    INDEX
    Explanations

    Commands and instructions

    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
     allowable
    0.63
     &/
    0.55
     stalwart
    0.52
    Conversely
    0.50
     continual
    0.49
     decked
    0.47
     appreciably
    0.46
     outfitted
    0.46
    <unused2123>
    0.46
     демонстри
    0.43
    POSITIVE LOGITS
     touristic
    0.98
     ressources
    0.95
     exercice
    0.94
     advices
    0.94
     exercices
    0.89
     planification
    0.88
     restauration
    0.86
     partecip
    0.84
     bellow
    0.82
    ´
    0.81
    Activations Density 0.031%

    No Known Activations