© 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. 16-GEMMASCOPE-2-RES-262K
    7. 3768
    Prev
    Next
    INDEX
    Explanations

    identifying specific types of entities or concepts

    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_16_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
     VISA
    0.50
    ὺς
    0.48
     Twisted
    0.46
     Misc
    0.44
    კის
    0.43
    áciu
    0.43
    畸
    0.42
     Gillian
    0.41
     Mega
    0.40
     Cardio
    0.40
    POSITIVE LOGITS
     стрем
    0.59
     сочета
    0.56
     dlatego
    0.55
    ırm
    0.54
     amenazas
    0.50
     estab
    0.50
     ሙ
    0.49
     вследствие
    0.49
     ע
    0.49
    ע
    0.49
    Activations Density 0.000%

    No Known Activations