© 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-65K
    7. 36114
    Prev
    Next
    INDEX
    Explanations

    interpret results or shifted stance

    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_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
    prüfung
    0.54
     όταν
    0.51
    または
    0.46
    шому
    0.44
    utérus
    0.43
    𝒌
    0.43
     посто
    0.42
    >;</
    0.41
    AutoStabilise
    0.41
    㸮
    0.41
    POSITIVE LOGITS
     opinions
    0.47
     malu
    0.46
     laughable
    0.45
     Hos
    0.44
     Kral
    0.41
     nes
    0.41
     Nes
    0.41
     opiniones
    0.40
     begr
    0.40
     Kür
    0.39
    Activations Density 0.011%

    No Known Activations