© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 64832
    Prev
    Next
    INDEX
    Explanations

    pool

    np_acts-logits-general · gemini-2.5-flash-lite

    were traveling, sold in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     socialist
    0.52
     cropland
    0.51
     abolish
    0.51
    -}
    0.49
     adopt
    0.47
     depict
    0.46
     dona
    0.45
    =}
    0.45
    య
    0.45
     renewables
    0.45
    POSITIVE LOGITS
     Pairing
    0.45
    toire
    0.44
     Dressing
    0.44
     Freizeit
    0.44
     Guille
    0.43
     indietro
    0.43
     Kirche
    0.42
     στους
    0.42
     Complement
    0.41
     Adapter
    0.41
    Activations Density 0.000%

    No Known Activations