© 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. 116529
    Prev
    Next
    INDEX
    Explanations

    website actions and destinations

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

    text length specifications

    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
    ために
    0.47
    关
    0.41
     cottages
    0.41
     rechargeable
    0.40
    риз
    0.40
     Bamber
    0.39
     وید
    0.39
    蕊
    0.39
     ද
    0.38
    ダイヤモンド
    0.38
    POSITIVE LOGITS
    ReturnValue
    0.48
    expected
    0.46
    𝐚
    0.46
    CRT
    0.45
     marginRight
    0.44
    CartVO
    0.44
    KeyboardView
    0.43
     friv
    0.43
    חר
    0.42
    orini
    0.42
    Activations Density 0.001%

    No Known Activations