© 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. 52305
    Prev
    Next
    INDEX
    Explanations

    dates and events

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

    designing and building

    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
     Arran
    0.51
     Красно
    0.50
    orini
    0.49
    ulph
    0.48
    )|\
    0.47
    ūd
    0.47
     Khat
    0.45
    ッグ
    0.45
    brack
    0.45
    irea
    0.45
    POSITIVE LOGITS
     remit
    0.50
     vote
    0.50
     لينك
    0.49
    ፈ
    0.46
     entryway
    0.45
     centerpiece
    0.45
     ו
    0.45
     unleash
    0.44
     entry
    0.43
    ה
    0.43
    Activations Density 0.000%

    No Known Activations