© 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. 43391
    Prev
    Next
    INDEX
    Explanations

    describing concepts and states

    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
     malignancy
    0.54
     sécur
    0.53
     ரே
    0.44
     уен
    0.43
    濆
    0.42
     сопер
    0.42
    ሰብ
    0.42
    فضل
    0.41
    圭
    0.41
    豊
    0.41
    POSITIVE LOGITS
     ik
    0.55
    ik
    0.46
     Aaron
    0.46
     kar
    0.46
    un
    0.46
     Chang
    0.46
    jew
    0.46
    Chang
    0.45
    ras
    0.45
     Gh
    0.45
    Activations Density 0.004%

    No Known Activations