© 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. 99213
    Prev
    Next
    INDEX
    Explanations

    house rent party

    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
    Качество
    -0.84
    screenWidth
    -0.73
    cstdio
    -0.73
     Familien
    -0.72
    žne
    -0.69
    ValuePair
    -0.69
    digheid
    -0.69
     enriquec
    -0.68
    strength
    -0.68
    cza
    -0.68
    POSITIVE LOGITS
     buffer
    1.63
     ByteBuffer
    1.63
     buffers
    1.63
    ByteBuffer
    1.62
    Buffer
    1.48
     Buffer
    1.34
     buf
    1.21
    buffer
    1.20
    buffers
    1.08
    Buffers
    1.06
    Activations Density 0.014%

    No Known Activations