© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 21207
    Prev
    Next
    INDEX
    Explanations

    extra + specific word

    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_10/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
     The
    -2.27
     technisch
    -2.14
     of
    -2.09
    \
    -2.06
    皤
    -1.94
    V
    -1.93
    {
    -1.84
     mostrando
    -1.80
                        
    -1.79
    (
    -1.79
    POSITIVE LOGITS
    Even
    2.31
     giyim
    2.28
    Though
    2.17
    Surprisingly
    2.17
    Although
    2.16
    Having
    2.13
    URIDAD
    2.13
     görünü
    2.09
     poner
    2.09
    Usually
    2.06
    Activations Density 0.011%

    No Known Activations