© 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. 57075
    Prev
    Next
    INDEX
    Explanations

    mode of transportation

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

    management and power dynamics

    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
    Sour
    0.51
    鹄
    0.48
    pecific
    0.45
    ｳ
    0.44
     dearth
    0.43
    明白了
    0.43
    قول
    0.41
    밭
    0.41
    ChooseCharacter
    0.40
    SOS
    0.40
    POSITIVE LOGITS
     Races
    0.52
     mãi
    0.50
     později
    0.49
     পড়িয়া
    0.47
     races
    0.46
     Racing
    0.45
     Kids
    0.44
     похід
    0.44
    ือบ
    0.43
     SeekBar
    0.43
    Activations Density 0.000%

    No Known Activations