© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 12283
    Prev
    Next
    INDEX
    Explanations

    early graduating, alternative education

    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
    bezier
    -0.84
    Ầ
    -0.76
     стек
    -0.73
    extraction
    -0.69
    FWIW
    -0.68
    anal
    -0.68
     vernac
    -0.67
    粜
    -0.67
     植
    -0.66
    بوب
    -0.66
    POSITIVE LOGITS
     dual
    1.30
     Early
    1.27
     virtual
    1.22
     Virtual
    1.21
    Early
    1.16
     online
    1.16
     concurrent
    1.15
     Dual
    1.11
     early
    1.09
    dual
    1.09
    Activations Density 0.016%

    No Known Activations