© 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. 243430
    Prev
    Next
    INDEX
    Explanations

    business cost

    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
    ᇁ
    0.56
     TECHN
    0.55
     lado
    0.53
     DRM
    0.52
     nascimento
    0.52
     IRAS
    0.52
     ASPECTS
    0.52
     SECRET
    0.51
     CERN
    0.51
     NIST
    0.50
    POSITIVE LOGITS
    concerned
    0.44
    indexing
    0.41
    j
    0.39
    Output
    0.38
    zed
    0.38
    ৈত
    0.38
    angs
    0.38
    perse
    0.38
    রিদ্র
    0.38
    تور
    0.38
    Activations Density 0.001%

    No Known Activations