© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 221953
    Prev
    Next
    INDEX
    Explanations

    oxidation and appraisal

    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_40_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
    摞
    0.42
    ret
    0.40
    buckets
    0.39
    conduct
    0.38
    بك
    0.37
    itations
    0.36
    reo
    0.35
    spolit
    0.35
    篓
    0.35
    bought
    0.35
    POSITIVE LOGITS
    (',
    0.45
     appraisal
    0.44
     idiot
    0.41
     assigned
    0.40
     Assigned
    0.39
     Oxidation
    0.39
     oxidation
    0.39
     Appraisal
    0.39
     apprais
    0.38
     appraisals
    0.38
    Activations Density 0.000%

    No Known Activations