© 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. 36995
    Prev
    Next
    INDEX
    Explanations

    isArray, Middle, Proxmox

    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
     darkest
    0.46
     kein
    0.44
     thresholds
    0.44
     L
    0.43
     했습니다
    0.43
     threshold
    0.42
     Picasso
    0.42
     الل
    0.42
     D
    0.41
    m
    0.41
    POSITIVE LOGITS
     किंवा
    0.45
     அல்லது
    0.44
     insofar
    0.44
    MyToolkit
    0.43
    Deployed
    0.41
     അല്ലെങ്കിൽ
    0.40
    LOTREntity
    0.39
    或者
    0.39
    sofar
    0.38
    ,【
    0.38
    Activations Density 0.005%

    No Known Activations