© 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. 20893
    Prev
    Next
    INDEX
    Explanations

    analytical judgements

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

    online context and filters

    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
     щоб
    0.49
     علشان
    0.49
     защото
    0.47
    Чтобы
    0.45
    этому
    0.45
    हालांकि
    0.45
    acquisto
    0.44
    ᅩ
    0.44
     equipado
    0.44
     díky
    0.43
    POSITIVE LOGITS
     abstractions
    0.47
    :
    0.46
     from
    0.46
     judgements
    0.43
     analytical
    0.42
     von
    0.42
     external
    0.42
     arising
    0.41
     analytic
    0.41
     therefrom
    0.41
    Activations Density 0.000%

    No Known Activations