© 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. 114812
    Prev
    Next
    INDEX
    Explanations

    repeated sequences or customers

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

    explaining why

    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
    ทร
    0.47
     pubescent
    0.46
    以降
    0.45
    isor
    0.44
    rates
    0.44
    浅
    0.43
    त्रा
    0.43
    ness
    0.42
     minimized
    0.42
     दर्शाता
    0.42
    POSITIVE LOGITS
    ichtig
    0.48
    Inn
    0.46
     frío
    0.45
     Fundação
    0.45
    窨
    0.44
     genau
    0.43
     குளிர்
    0.43
    Duty
    0.43
     الصحي
    0.42
    ัฐ
    0.42
    Activations Density 0.000%

    No Known Activations