© 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. 30873
    Prev
    Next
    INDEX
    Explanations

    Sun, Saturn, planets, astrology

    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
    tagHelperRunner
    -0.98
    Sklici
    -0.96
     parec
    -0.91
    ganj
    -0.84
     molte
    -0.84
     svilupp
    -0.82
    Prijs
    -0.82
     migliorare
    -0.82
     risolvere
    -0.82
    seteq
    -0.81
    POSITIVE LOGITS
     in
    1.52
     square
    0.90
     exact
    0.90
     ruling
    0.89
    square
    0.83
     retrograde
    0.82
     opposition
    0.79
     Opposition
    0.79
    ruler
    0.79
     at
    0.78
    Activations Density 0.007%

    No Known Activations