© 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. 33647
    Prev
    Next
    INDEX
    Explanations

    category management

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

    measurement units and common phrases

    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
    ة
    0.65
    -
    0.58
    ை
    0.47
    Par
    0.47
     (
    0.46
    M
    0.46
    قيق
    0.45
    市政
    0.45
    Field
    0.45
    亘
    0.44
    POSITIVE LOGITS
     telefon
    0.54
    telefon
    0.53
     centimetres
    0.53
     centimeters
    0.52
    英寸
    0.52
     mobilize
    0.51
    reflectionCamera
    0.51
     वायरलेस
    0.51
     sellers
    0.50
     probleem
    0.50
    Activations Density 0.000%

    No Known Activations