© 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. 32454
    Prev
    Next
    INDEX
    Explanations

    discussion of related art

    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
     giz
    -0.88
    udia
    -0.88
    anol
    -0.86
     Alimentos
    -0.85
    цыі
    -0.84
    tabil
    -0.81
    Policy
    -0.80
    IDIA
    -0.80
     IAC
    -0.80
    taal
    -0.79
    POSITIVE LOGITS
     tax
    0.93
    stalline
    0.91
     potential
    0.91
     certain
    0.90
     taxation
    0.86
     comparisons
    0.83
     factors
    0.80
     legal
    0.80
     risks
    0.79
    代わりに
    0.79
    Activations Density 0.007%

    No Known Activations