© 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. 4468
    Prev
    Next
    INDEX
    Explanations

    sentence boundary continuations

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

    misrepresentation and punishments

    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
     subsections
    0.29
    unächst
    0.27
     cheeks
    0.27
    ンドウ
    0.26
    JECTION
    0.26
     transceiver
    0.26
    ⴷ
    0.26
     subsection
    0.25
     hemispheres
    0.25
     analogue
    0.25
    POSITIVE LOGITS
     Hopefully
    0.37
     అది
    0.34
     😉
    0.33
     সেটাও
    0.32
     иногда
    0.32
     They
    0.31
     Sadly
    0.30
     🙂
    0.30
     That
    0.29
     அது
    0.29
    Activations Density 0.741%

    No Known Activations