© 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. 111142
    Prev
    Next
    INDEX
    Explanations

    regulation and regression

    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
    ного
    0.77
     is
    0.69
     reorgan
    0.68
     paramet
    0.65
    ä
    0.64
     categor
    0.63
    >
    0.62
     hypothes
    0.61
     pronounce
    0.61
    ț
    0.61
    POSITIVE LOGITS
    al
    1.03
    on
    0.96
    ار
    0.91
    ак
    0.90
    ু
    0.89
    us
    0.85
    rég
    0.85
    دی
    0.84
    ли
    0.80
    is
    0.80
    Activations Density 0.042%

    No Known Activations