© 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. 168853
    Prev
    Next
    INDEX
    Explanations

    affiliate marketing

    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
    。
    0.64
    erate
    0.50
    。\
    0.47
    loé
    0.45
    orado
    0.44
     petite
    0.43
     souci
    0.42
    ipe
    0.42
    ਼
    0.42
    ى
    0.41
    POSITIVE LOGITS
     bialgebras
    0.49
     lagoons
    0.49
     ૩
    0.48
     সার্ভ
    0.48
     ocult
    0.47
     dotyczą
    0.46
     ABP
    0.46
     ऋण
    0.46
     গম
    0.46
     NCB
    0.46
    Activations Density 0.000%

    No Known Activations