© 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. 167677
    Prev
    Next
    INDEX
    Explanations

    adds porosity or specific details

    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
     tamen
    0.37
    是一位
    0.37
    ogramDetails
    0.37
     excepted
    0.36
    shr
    0.36
     hài
    0.36
    吭
    0.36
    XP
    0.35
     interval
    0.35
     vina
    0.35
    POSITIVE LOGITS
    FIED
    0.44
    電話
    0.42
    formulario
    0.41
    BI
    0.40
    regarding
    0.39
    ミ
    0.39
    ֆ
    0.39
     मुखर्जी
    0.39
     독립
    0.38
     regarding
    0.38
    Activations Density 0.000%

    No Known Activations