© 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. 195696
    Prev
    Next
    INDEX
    Explanations

    action and its object

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

    specific nouns and short phrases

    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
    ｪ
    0.55
     necrotic
    0.55
     vasculature
    0.49
    𝓎
    0.47
     apnea
    0.46
     ainfi
    0.46
    箱
    0.46
     ERK
    0.46
    ژن
    0.45
     контракт
    0.45
    POSITIVE LOGITS
    Pure
    0.48
     Administration
    0.45
     Pure
    0.45
    েল
    0.44
    க்
    0.43
    撂
    0.43
     Words
    0.43
     Mud
    0.42
     Park
    0.42
    X
    0.42
    Activations Density 0.000%

    No Known Activations