© 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. 160020
    Prev
    Next
    INDEX
    Explanations

    yourself, themselves, meet, harm

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

    natural, but, slowly, Free, began, simply

    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
     WHY
    0.55
    OCO
    0.51
    Y
    0.50
    YD
    0.49
    ทั่วไป
    0.48
    Tareas
    0.48
    वी
    0.48
    izmi
    0.48
    IOR
    0.48
    LEA
    0.47
    POSITIVE LOGITS
     była
    0.44
    舉辦
    0.43
    눴
    0.42
    另一种
    0.41
    ፴
    0.41
     Hemisphere
    0.41
     fifteenth
    0.41
     Gastgeber
    0.40
     sensory
    0.40
     nieuw
    0.39
    Activations Density 0.000%

    No Known Activations