© 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. 109807
    Prev
    Next
    INDEX
    Explanations

    conclusion:

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

    conclusion:

    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
     conclusions
    0.48
    тод
    0.46
     soit
    0.46
    alic
    0.46
     пункт
    0.44
    aluminum
    0.44
    ফিন
    0.44
    휙
    0.44
     revêt
    0.43
    unuh
    0.43
    POSITIVE LOGITS
     Hope
    0.45
     সঞ্চ
    0.43
     আশা
    0.40
     hopes
    0.40
     Explo
    0.40
    قة
    0.39
     Lobby
    0.39
    Hope
    0.38
     भे
    0.38
     Ment
    0.37
    Activations Density 0.001%

    No Known Activations