© 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. 222412
    Prev
    Next
    INDEX
    Explanations

    technical and foreign terms

    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
     língua
    0.42
     il
    0.41
     Warwickshire
    0.40
    Cols
    0.39
     cigar
    0.38
     Eds
    0.38
    _____________
    0.38
     Deputies
    0.37
     côtes
    0.37
    )$.
    0.37
    POSITIVE LOGITS
    izando
    0.42
    Algorithm
    0.40
    ATEC
    0.38
    Flags
    0.38
     ڈیٹ
    0.38
    幻
    0.37
    ポスト
    0.36
    heny
    0.36
    Scal
    0.36
    Shock
    0.36
    Activations Density 0.000%

    No Known Activations