© 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. 31-GEMMASCOPE-2-RES-262K
    7. 91743
    Prev
    Next
    INDEX
    Explanations

    growth areas, personal crime, critical perspective

    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
    spun
    0.42
    circ
    0.41
    suitcase
    0.41
     zipped
    0.41
    sponge
    0.40
    strptime
    0.39
    ெ
    0.39
    ᓘ
    0.39
     仮
    0.39
     Messina
    0.38
    POSITIVE LOGITS
     wilayah
    0.48
    ustering
    0.47
    api
    0.47
     VoIP
    0.45
     zuvor
    0.44
     Sebelumnya
    0.44
    épid
    0.44
     ehemal
    0.43
     technologie
    0.42
     disponibili
    0.42
    Activations Density 0.001%

    No Known Activations