© 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. 186553
    Prev
    Next
    INDEX
    Explanations

    selection, spot, message, useful, review

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

    store layouts

    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
    science
    0.45
    }_{\
    0.44
     nisi
    0.44
    peace
    0.44
    ónio
    0.43
    }^{+
    0.40
     تنس
    0.40
     нау
    0.40
     दावे
    0.40
    ussie
    0.40
    POSITIVE LOGITS
    AB
    0.50
     calcS
    0.48
     SAB
    0.48
    ্ডি
    0.47
    IsValid
    0.46
    Item
    0.46
    Hospital
    0.45
    괵
    0.45
     cancels
    0.45
     arabe
    0.45
    Activations Density 0.002%

    No Known Activations