© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 48658
    Prev
    Next
    INDEX
    Explanations

    register your

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

    registering models, converting data, migrating

    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
     పాల
    0.49
     vagy
    0.43
    baa
    0.42
     islands
    0.41
     తర
    0.41
    সম্পাদকীয়
    0.40
     或者
    0.40
     或
    0.39
    skip
    0.39
    \\\
    0.39
    POSITIVE LOGITS
    내가
    0.56
     നടന്ന
    0.49
    ﻓ
    0.48
    ਓ
    0.48
    ירות
    0.47
    제를
    0.47
    십
    0.45
    iviato
    0.45
    できて
    0.45
    Ejercicio
    0.44
    Activations Density 0.000%

    No Known Activations