© 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. 66999
    Prev
    Next
    INDEX
    Explanations

    specific names or related entities

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

    ECU software implementation

    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
     vínculos
    0.46
     ngân
    0.44
     ké
    0.44
    保
    0.43
    پار
    0.43
     rượu
    0.42
     previewBuilder
    0.41
    갱
    0.41
    시설
    0.40
    了一眼
    0.40
    POSITIVE LOGITS
    ॅ
    0.51
    lerine
    0.48
     ABS
    0.47
     absorbance
    0.47
    चणी
    0.47
    use
    0.46
    romechanical
    0.46
     Edo
    0.45
    ళ్ల
    0.45
     HIP
    0.44
    Activations Density 0.000%

    No Known Activations