© 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. 181271
    Prev
    Next
    INDEX
    Explanations

    GSTR and tax codes

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

    fine-tuning constants

    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
     ciencias
    0.44
    dyl
    0.41
     scienze
    0.41
    ase
    0.40
    ξη
    0.40
    علوم
    0.40
    '
    0.40
    ур
    0.40
     allere
    0.40
    eb
    0.40
    POSITIVE LOGITS
     Aries
    0.48
     калі
    0.46
     Pratap
    0.44
     مارت
    0.44
     millis
    0.43
     mandala
    0.43
     diurnal
    0.43
    otricha
    0.42
     Sì
    0.42
     centering
    0.42
    Activations Density 0.001%

    No Known Activations