© 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. 31-GEMMASCOPE-2-RES-262K
    7. 84817
    Prev
    Next
    INDEX
    Explanations

    understand, need, prompt, Name, crushes

    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_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
    Thunder
    0.44
    лата
    0.44
     obrigado
    0.43
    На
    0.43
    蛟
    0.42
     facilmente
    0.42
    тран
    0.42
     miniature
    0.41
    Trick
    0.41
    梦
    0.41
    POSITIVE LOGITS
     adhesion
    0.46
     adhesions
    0.45
    ಳಿ
    0.45
    皚
    0.44
    銆
    0.43
    etzes
    0.42
     periodista
    0.42
     ditth
    0.42
     irradiation
    0.42
     accords
    0.41
    Activations Density 0.000%

    No Known Activations