© 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. 36051
    Prev
    Next
    INDEX
    Explanations

    labels and keys

    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
    django
    0.49
    springframework
    0.45
    ('/');
    0.44
    /');
    0.43
    ahren
    0.42
    và
    0.42
    hu
    0.42
    apache
    0.42
    dataset
    0.42
    ca
    0.41
    POSITIVE LOGITS
     풀
    0.47
     į
    0.46
    یشه
    0.45
     של
    0.44
     Anti
    0.43
    мость
    0.43
     mė
    0.43
    ність
    0.43
     سريع
    0.42
     réduite
    0.42
    Activations Density 0.029%

    No Known Activations