© 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. 93709
    Prev
    Next
    INDEX
    Explanations

    explanations of concepts and effects

    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
    Bond
    0.47
    Enh
    0.45
    Barrier
    0.45
    Dick
    0.43
    粝
    0.43
    Extension
    0.43
    ദ്യ
    0.43
    Fit
    0.42
     Bond
    0.42
    Audit
    0.42
    POSITIVE LOGITS
     stressors
    0.55
    ια
    0.53
    ㄺ
    0.48
     conocimientos
    0.47
     factores
    0.47
     جيڪ
    0.46
     avocados
    0.46
     plufieurs
    0.46
     facteur
    0.45
     больных
    0.45
    Activations Density 0.000%

    No Known Activations