© 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. 35002
    Prev
    Next
    INDEX
    Explanations

    contrast, implication, qualification

    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
    če
    0.45
     ambientale
    0.44
     hatred
    0.43
    lighet
    0.43
     士
    0.41
    리면
    0.41
     区
    0.41
     NOTHING
    0.40
    či
    0.40
     블
    0.40
    POSITIVE LOGITS
    ັກ
    0.50
    ⌝
    0.46
    എന്ന
    0.45
    )*((
    0.45
    izr
    0.44
    ത്ത
    0.44
    日前
    0.42
    خراج
    0.42
    امر
    0.42
    خبر
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.