© 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. 208274
    Prev
    Next
    INDEX
    Explanations

    financial conditions and reservations

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

    employment, name, waters

    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
     fontFamily
    0.44
     Ана
    0.43
     colo
    0.42
    થી
    0.42
    خل
    0.41
     nanotubes
    0.41
    ドリ
    0.41
    듄
    0.41
    シングル
    0.40
     ultraf
    0.40
    POSITIVE LOGITS
    aj
    0.48
    arr
    0.48
    repe
    0.47
    arrange
    0.47
     स्पोर्ट
    0.46
    radi
    0.45
    ारा
    0.45
    ras
    0.45
    ili
    0.45
    on
    0.44
    Activations Density 0.002%

    No Known Activations