© 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. 237422
    Prev
    Next
    INDEX
    Explanations

    turn to

    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
     Bá
    0.47
     黃
    0.47
     해결
    0.45
     vrijdag
    0.45
     vormen
    0.44
     żół
    0.44
     anthracite
    0.44
     sixteenth
    0.44
     ücretsiz
    0.44
     formazione
    0.44
    POSITIVE LOGITS
    탯
    0.44
     відповідно
    0.43
    ว่า
    0.43
    ્યુ
    0.43
    ว่าเป็น
    0.43
    ద్ది
    0.43
    Fitting
    0.43
    MessageType
    0.42
    มาะ
    0.42
    ంచెం
    0.41
    Activations Density 0.001%

    No Known Activations