© 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. 57992
    Prev
    Next
    INDEX
    Explanations

    stock declined

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

    JSON documents

    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
    comput
    0.54
    ፩
    0.51
    ন্দ্র
    0.49
    ष्ठी
    0.49
     Classical
    0.46
     prí
    0.46
     Computed
    0.46
    鹼
    0.46
     gewüns
    0.45
     Computational
    0.45
    POSITIVE LOGITS
     alone
    0.45
     organised
    0.45
     lodged
    0.44
     organized
    0.43
     (
    0.42
    chak
    0.41
     leggera
    0.41
    йдёт
    0.41
     kicked
    0.40
     ineligible
    0.40
    Activations Density 0.000%

    No Known Activations