© 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. 27011
    Prev
    Next
    INDEX
    Explanations

    allowing smaller, bypass, nanodevices

    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
    ין
    0.54
    tees
    0.53
    ევ
    0.51
    Odds
    0.50
    Remarks
    0.50
    Е
    0.50
    АК
    0.50
    Так
    0.49
    तक
    0.48
    톄
    0.48
    POSITIVE LOGITS
     Bold
    0.42
     story
    0.41
    वलं
    0.41
    chend
    0.40
     felt
    0.40
     bold
    0.40
     Ministry
    0.40
     Justice
    0.39
     Brazil
    0.39
     Growth
    0.39
    Activations Density 0.005%

    No Known Activations