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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 42352
    Prev
    Next
    INDEX
    Explanations

    tesseract blossoming fractal

    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
    3
    0.48
    2
    0.46
     transcripts
    0.44
    7
    0.44
    rainer
    0.43
    4
    0.43
     elimination
    0.42
    9
    0.42
    ions
    0.42
     journalists
    0.41
    POSITIVE LOGITS
     verfü
    0.48
     ಭ
    0.46
     Populate
    0.45
     ܗ
    0.44
     preparando
    0.43
     मोठ
    0.41
     pengetahuan
    0.41
     recib
    0.41
     మహ
    0.41
     préparer
    0.41
    Activations Density 0.002%

    No Known Activations