© 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. 53-GEMMASCOPE-2-RES-262K
    7. 11521
    Prev
    Next
    INDEX
    Explanations

    an open

    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_53_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
     S
    0.66
     الس
    0.53
    S
    0.50
     Bur
    0.47
    Bur
    0.46
    Gr
    0.43
     С
    0.41
    G
    0.41
    Bal
    0.40
    Ｓ
    0.40
    POSITIVE LOGITS
    carb
    0.38
    martin
    0.36
     martin
    0.36
    Martin
    0.34
    掣
    0.33
    methyl
    0.33
    spin
    0.32
     MARTIN
    0.32
    supset
    0.31
     campaña
    0.31
    Activations Density 0.018%

    No Known Activations