© 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. 151720
    Prev
    Next
    INDEX
    Explanations

    end punctuation and phrases

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

    actions followed by state or direction

    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
     दी
    0.48
    ዕ
    0.46
    尚未
    0.45
    þ
    0.44
     γεγον
    0.43
     περισ
    0.43
     þ
    0.43
     diễn
    0.43
    以上の
    0.43
     gneiss
    0.43
    POSITIVE LOGITS
    ).
    0.51
    =.
    0.45
    \,.
    0.45
    ina
    0.44
    کی
    0.43
    -.
    0.42
     DETECTION
    0.42
    «.
    0.41
    ؟
    0.40
    तरे
    0.40
    Activations Density 0.001%

    No Known Activations