© 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-65K
    7. 20098
    Prev
    Next
    INDEX
    Explanations

    introduces explanation of what something allows or is

    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
     inoltre
    0.49
     സ്ത്രീ
    0.44
     Ayrıca
    0.43
    ğer
    0.42
     ಬಾ
    0.42
    ൦
    0.42
    Finalmente
    0.42
     Finalmente
    0.42
     voulait
    0.40
    鮒
    0.40
    POSITIVE LOGITS
     type
    0.41
     باعث
    0.37
     بيكون
    0.37
     kind
    0.36
     caused
    0.36
     formed
    0.36
    caused
    0.36
     phenomenon
    0.35
     massive
    0.35
     phenomena
    0.35
    Activations Density 0.009%

    No Known Activations