© 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. 241363
    Prev
    Next
    INDEX
    Explanations

    geographic or descriptive phrases

    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
     എല്ലാവ
    0.58
     അങ്ങനെ
    0.55
    }">${
    0.50
    efficiency
    0.50
     എല്ലാ
    0.49
    halen
    0.49
     કાર્ય
    0.48
     iedere
    0.48
    ాగ
    0.48
     Pflege
    0.48
    POSITIVE LOGITS
    :
    0.47
     quenched
    0.46
     quench
    0.43
     DIAG
    0.43
     diag
    0.43
     metastability
    0.42
     singularities
    0.42
     synth
    0.41
     landmarks
    0.41
     seminal
    0.41
    Activations Density 0.001%

    No Known Activations