© 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. 142209
    Prev
    Next
    INDEX
    Explanations

    building a new life

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

    syntactic sugar

    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
    sum
    0.59
    sil
    0.59
    p
    0.57
    st
    0.57
    -
    0.57
    m
    0.56
     University
    0.52
    University
    0.51
    з
    0.50
    ס
    0.50
    POSITIVE LOGITS
     இறு
    0.56
     condições
    0.53
     भर्ती
    0.51
     கரு
    0.51
     actionMode
    0.51
    の方
    0.50
    𝓢
    0.49
     思う
    0.48
     এড
    0.48
     肌
    0.48
    Activations Density 0.000%

    No Known Activations