© 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. 135084
    Prev
    Next
    INDEX
    Explanations

    teamgroupchildrencomingpeaceNew

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

    Unlock potential, secrets, or exceptional qualities

    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
     öğrenciler
    0.58
    未知
    0.49
    
    0.49
    ็
    0.48
     памят
    0.46
    
    0.46
    稹
    0.46
    ്രാ
    0.46
     виртуа
    0.46
    BooleanField
    0.45
    POSITIVE LOGITS
    pin
    0.48
     ’
    0.44
     Infos
    0.44
    вле
    0.44
     grosso
    0.44
    ess
    0.43
     Só
    0.43
     Sunni
    0.43
    эння
    0.43
    }\,
    0.42
    Activations Density 0.000%

    No Known Activations