© 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. 3755
    Prev
    Next
    INDEX
    Explanations

    yes

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

    Yes, followed by punctuation

    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
     keySchedule
    0.37
     ateliers
    0.36
    ీల
    0.34
    ²)
    0.33
     বাঙ্গালীদের
    0.33
     ascor
    0.32
     pairs
    0.32
    INDOW
    0.32
     aigu
    0.32
     assessor
    0.32
    POSITIVE LOGITS
    !
    0.59
    ,
    0.49
    yes
    0.43
    !,
    0.42
    ،
    0.42
    Yes
    0.41
    yeah
    0.41
     Infatti
    0.38
    .
    0.37
    ！
    0.37
    Activations Density 0.094%

    No Known Activations