© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 53076
    Prev
    Next
    INDEX
    Explanations

    DateTime, ties, trees

    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_65k_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
    Berlin
    0.41
    max
    0.40
    linearity
    0.39
     Draw
    0.38
    onne
    0.36
     চূড়ান্ত
    0.36
     সন্ত্র
    0.36
    /}
    0.35
     discurso
    0.35
     max
    0.35
    POSITIVE LOGITS
    を提供する
    0.42
    を提供
    0.41
    ቶች
    0.41
    的目标
    0.39
    を追加
    0.39
     targeted
    0.38
     オ
    0.37
     забу
    0.37
    ייש
    0.37
     ከሆነ
    0.37
    Activations Density 0.000%

    No Known Activations