© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 95225
    Prev
    Next
    INDEX
    Explanations

    open source software

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

    Linux, Red Hat, and GPL

    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
    覺
    0.47
     Poem
    0.46
     poem
    0.45
    腳
    0.44
     omnip
    0.43
     décor
    0.42
     poems
    0.42
     fecal
    0.42
    ꫝ
    0.42
     horseback
    0.42
    POSITIVE LOGITS
    Linux
    0.73
     Linux
    0.67
    enterprise
    0.57
    Ubuntu
    0.56
    entreprise
    0.56
    linux
    0.54
    Enterprise
    0.52
    Software
    0.52
    AMD
    0.52
     Fedora
    0.51
    Activations Density 0.145%

    No Known Activations