© 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. 26234
    Prev
    Next
    INDEX
    Explanations

    closing in, credit verification, specific instructions

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

    mist curling around

    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
    l
    0.67
    c
    0.63
    r
    0.57
    n
    0.52
    0.51
    v
    0.50
        
    0.49
    샵
    0.48
    k
    0.48
    p
    0.48
    POSITIVE LOGITS
     اڈوں
    0.53
     بانک
    0.51
    FindingsResponse
    0.50
     त्याच्या
    0.48
     సర్
    0.48
    parvec
    0.48
     paranoia
    0.47
     வெங்க
    0.47
     supposition
    0.47
     redes
    0.46
    Activations Density 0.000%

    No Known Activations