© 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. 42079
    Prev
    Next
    INDEX
    Explanations

    examples include

    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
    त्रा
    0.48
    СТО
    0.41
     particular
    0.41
    
    0.40
    по
    0.40
     subjectivity
    0.39
     qualitatively
    0.38
     cumulative
    0.38
    пара
    0.38
     яв
    0.38
    POSITIVE LOGITS
    ☕
    0.43
    たくさんの
    0.43
    ammable
    0.40
     moż
    0.39
    eses
    0.39
    izable
    0.39
    ousands
    0.39
    suitable
    0.38
    alee
    0.38
     maraming
    0.37
    Activations Density 0.003%

    No Known Activations