© 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. 200071
    Prev
    Next
    INDEX
    Explanations

    control, deep, tells, especially, guitar, access

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

    complex concepts and sequences

    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
     bumpers
    0.47
    ®,
    0.46
    емов
    0.46
     sired
    0.46
     compatibles
    0.45
     indications
    0.44
     originals
    0.44
     explanations
    0.44
    _
    0.43
     premiums
    0.43
    POSITIVE LOGITS
    
    0.51
     chiam
    0.48
     تسجيل
    0.47
     दवाई
    0.47
     uży
    0.47
     použ
    0.47
     u
    0.46
    recording
    0.46
     イヤ
    0.46
     Quando
    0.45
    Activations Density 0.000%

    No Known Activations