© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 102752
    Prev
    Next
    INDEX
    Explanations

    Send us, hold of, advocate him

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

    high risk, high reward

    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
    ate
    0.51
    ogener
    0.46
    -
    0.44
    隀
    0.44
    (
    0.43
     Ein
    0.42
    ceptions
    0.42
    \
    0.42
    䢁
    0.42
    names
    0.41
    POSITIVE LOGITS
     предела
    0.60
     límites
    0.50
    ≳
    0.47
     преимущества
    0.47
     timescale
    0.47
     масштаб
    0.46
    𝕘
    0.46
     більш
    0.45
     compañía
    0.45
    ريب
    0.44
    Activations Density 0.004%

    No Known Activations