© 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. 53-GEMMASCOPE-2-RES-262K
    7. 13817
    Prev
    Next
    INDEX
    Explanations

    assignments, declarations, code blocks

    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_53_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
    $.;
    0.18
    ंगिक
    0.18
     वही
    0.17
    }+$
    0.17
     hostilities
    0.17
     उम्मीदवारों
    0.16
     exon
    0.16
     conditioned
    0.16
     amine
    0.16
     नयी
    0.16
    POSITIVE LOGITS
    (")
    0.18
    󠁿
    0.18
    ់
    0.18
    
    0.17
     drž
    0.17
    greSQL
    0.17
    (-)
    0.17
    صب
    0.16
     lacus
    0.16
    ("
    0.16
    Activations Density 0.903%

    No Known Activations