© 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. 125370
    Prev
    Next
    INDEX
    Explanations

    current phase

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

    explaining why or how

    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
    峠
    0.63
    O
    0.51
    DOCUMENT
    0.50
    ound
    0.50
    Imidazole
    0.49
    ots
    0.48
    CLOSE
    0.48
    도
    0.48
    OC
    0.48
    texture
    0.48
    POSITIVE LOGITS
     shrimp
    0.50
     检测
    0.48
     情况
    0.46
     Predicted
    0.45
    ப்பட்டது
    0.45
     चैप्ट
    0.44
    从此
    0.44
     bessere
    0.44
     meisjes
    0.44
     episódio
    0.43
    Activations Density 0.001%

    No Known Activations