© 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. 30360
    Prev
    Next
    INDEX
    Explanations

    regions, concepts, categories, and types

    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
     men
    0.30
     marble
    0.30
     .
    0.30
     meth
    0.30
     vague
    0.30
     m
    0.29
     poodle
    0.29
     |
    0.29
     he
    0.29
     tiny
    0.29
    POSITIVE LOGITS
     REGIUNI
    0.40
     ხელისუფ
    0.40
    𝟭
    0.38
    ירות
    0.38
    רו
    0.38
    Сегодня
    0.37
    重視
    0.36
    लेट
    0.36
    Yeni
    0.36
     రోజు
    0.36
    Activations Density 0.110%

    No Known Activations