© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1033
    Prev
    Next
    INDEX
    Explanations

    camp or side

    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
     filament
    -0.78
    ственных
    -0.75
    ynth
    -0.75
    该公司
    -0.73
     rulers
    -0.73
    iosa
    -0.69
    热点
    -0.69
     nivel
    -0.69
    adə
    -0.69
    TargetApi
    -0.69
    POSITIVE LOGITS
     camp
    6.06
     camps
    4.81
    camp
    4.47
    Camp
    3.84
     Camp
    3.70
    camps
    3.70
     CAMP
    3.44
     Camps
    3.31
    CAMP
    3.19
     лагер
    3.08
    Activations Density 0.062%

    No Known Activations