© 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. 71103
    Prev
    Next
    INDEX
    Explanations

    positive direction signs

    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
     Kaitlyn
    0.46
     shadowy
    0.46
     gelap
    0.45
    貥
    0.45
     Κο
    0.44
     โ
    0.42
     disruptions
    0.41
     torches
    0.40
     Sylvain
    0.40
     Torino
    0.40
    POSITIVE LOGITS
    estados
    0.56
     государства
    0.46
    اد
    0.46
    лся
    0.45
    াজের
    0.44
    ера
    0.44
    ান্ড
    0.43
    Electrical
    0.42
    ⵍ
    0.42
     pluck
    0.41
    Activations Density 0.006%

    No Known Activations