© 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. 156892
    Prev
    Next
    INDEX
    Explanations

    Act, waterways, bleak, future

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

    recurring themes, dream signs

    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
     hidrógeno
    0.49
     Đấy
    0.48
    ഡിയ
    0.47
     スーパー
    0.46
     improperly
    0.46
     Aeronaut
    0.46
     မ
    0.45
     superconducting
    0.45
     Sistem
    0.45
     נע
    0.45
    POSITIVE LOGITS
    개가
    0.53
     स्थान
    0.46
    굴
    0.46
    遍
    0.46
    四
    0.46
     tenets
    0.45
    नाथन
    0.45
    世
    0.45
    軍
    0.45
    тор
    0.44
    Activations Density 0.000%

    No Known Activations