© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77992
    Prev
    Next
    INDEX
    Explanations

    Here we, the objective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    こんな
    -0.76
     荣耀
    -0.75
     kidding
    -0.75
    APER
    -0.73
    сем
    -0.73
    JUST
    -0.72
    akujem
    -0.72
    quins
    -0.71
    ierungs
    -0.70
    Diego
    -0.70
    POSITIVE LOGITS
    pointed
    0.85
    AnimationsModule
    0.84
    paddingVertical
    0.84
    会う
    0.82
    argp
    0.80
    checkpoint
    0.79
    hundred
    0.77
    是小
    0.77
    钤
    0.76
    fff
    0.75
    Activations Density 0.000%

    No Known Activations