© 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. 168862
    Prev
    Next
    INDEX
    Explanations

    prevention and award

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

    explain quantum physics

    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
    ॅक
    0.52
     septembre
    0.49
     diciembre
    0.48
     Pä
    0.47
     przysz
    0.46
    꿨
    0.45
     semana
    0.45
    几天
    0.44
     agosto
    0.43
     febrero
    0.43
    POSITIVE LOGITS
    軸
    0.53
     當
    0.50
     並
    0.49
    })
    0.48
    Alignment
    0.46
    平面
    0.45
    Button
    0.44
    Namespace
    0.44
    Reason
    0.44
     jeweils
    0.44
    Activations Density 0.002%

    No Known Activations