© 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. 31200
    Prev
    Next
    INDEX
    Explanations

    completing common phrases

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

    identity theft and fraud

    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
    Isopropyl
    0.49
    Starter
    0.44
    棗
    0.44
    Resolver
    0.43
    經驗
    0.43
    㭉
    0.43
    栻
    0.42
     randint
    0.41
    Ϩ
    0.41
    DEL
    0.40
    POSITIVE LOGITS
    quels
    0.54
     felonies
    0.51
     moieties
    0.50
     quotas
    0.50
     comedies
    0.50
     hostages
    0.50
     horrend
    0.48
     catastrophes
    0.47
     voltages
    0.47
     speeches
    0.46
    Activations Density 0.000%

    No Known Activations