© 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. 23086
    Prev
    Next
    INDEX
    Explanations

    rail line

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

    ancient river

    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
     ganas
    0.43
    ﻜ
    0.43
    কর্মী
    0.42
     regreso
    0.42
     kolay
    0.42
    얽
    0.41
     लौटने
    0.41
    ㅋㅋㅋㅋㅋㅋㅋㅋ
    0.40
    段階
    0.40
    න්ත
    0.40
    POSITIVE LOGITS
    പ്പിച്ച
    0.49
     інтер
    0.48
    ĭ
    0.48
    ósz
    0.48
    Nom
    0.47
     interd
    0.47
    nu
    0.47
    可以看到
    0.45
    чним
    0.45
    as
    0.44
    Activations Density 0.000%

    No Known Activations