© 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. 25995
    Prev
    Next
    INDEX
    Explanations

    myths and specific things

    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
    es
    0.49
    em
    0.44
    endon
    0.43
    ř
    0.43
    False
    0.43
    izaciones
    0.43
    序列
    0.42
    ／
    0.42
    oringa
    0.41
    sprach
    0.41
    POSITIVE LOGITS
     imply
    0.46
     commer
    0.43
    飄
    0.42
     hassle
    0.42
     comparatively
    0.42
     buenas
    0.42
    ीजन
    0.42
     aank
    0.42
     boar
    0.41
     oub
    0.41
    Activations Density 0.000%

    No Known Activations