© 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. 64295
    Prev
    Next
    INDEX
    Explanations

    interpretation

    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
    estimated
    -1.14
    enderror
    -1.02
    valdi
    -0.96
    raits
    -0.94
     fhort
    -0.94
    További
    -0.93
    orso
    -0.91
     metoda
    -0.91
    怦
    -0.91
    Estimates
    -0.90
    POSITIVE LOGITS
     interpretation
    2.61
     interpretations
    2.13
     Interpretation
    2.11
    interpretation
    2.03
     interpreted
    2.02
     interpret
    1.98
     interpreta
    1.85
    Interpretation
    1.85
     interpreting
    1.84
    interpret
    1.80
    Activations Density 0.113%

    No Known Activations