© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 662
    Prev
    Next
    INDEX
    Explanations

    ISSN and publication formats

    np_acts-logits-general · gemini-2.5-flash-lite

    places and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    KindOfClass
    0.46
     వరు
    0.44
     kinases
    0.43
     fieldwork
    0.41
    Pojo
    0.40
    橼
    0.40
     sürekli
    0.40
     slaw
    0.39
     autocorrelation
    0.39
     öğrenciler
    0.39
    POSITIVE LOGITS
    2
    0.37
    1
    0.36
    4
    0.35
    0.34
    opa
    0.34
    英雄
    0.34
    OPA
    0.33
    oi
    0.33
    ulte
    0.33
     BG
    0.32
    Activations Density 0.000%

    No Known Activations