© 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. 90676
    Prev
    Next
    INDEX
    Explanations

    highest combined oceanic and land temps

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

    contribution continues name

    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
    entry
    0.49
    owie
    0.48
    ۷
    0.48
    ombang
    0.46
    eti
    0.45
    mannschaft
    0.45
    ąda
    0.45
    asadd
    0.45
    pse
    0.44
    ilst
    0.43
    POSITIVE LOGITS
     lotions
    0.52
     cotton
    0.51
    ('|
    0.51
    ନ୍ଦ
    0.50
     contributes
    0.50
     allusion
    0.49
     compensates
    0.47
     succede
    0.46
    ங்க
    0.46
     contribution
    0.46
    Activations Density 0.000%

    No Known Activations