© 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. 53350
    Prev
    Next
    INDEX
    Explanations

    quantities and calculations

    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
     γ
    0.49
     συν
    0.48
     cheer
    0.46
     quatro
    0.46
     suas
    0.45
    𝗕
    0.43
     kinh
    0.43
     עו
    0.43
     masc
    0.42
     de
    0.42
    POSITIVE LOGITS
    ;
    0.51
    ဟာ
    0.46
     Validators
    0.45
     Contracts
    0.44
     Victims
    0.43
    রাও
    0.41
    лия
    0.41
    动态
    0.41
    valmentaja
    0.41
     paddingTop
    0.40
    Activations Density 0.002%

    No Known Activations