© 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. 36391
    Prev
    Next
    INDEX
    Explanations

    where clauses for filtering data

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

    SQL WHERE clause conditions

    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
     Freunde
    0.44
    search
    0.42
     строительства
    0.41
    عادة
    0.41
    மா
    0.41
     výrob
    0.40
     Schwarzen
    0.40
    데
    0.40
    setSelected
    0.40
    propelled
    0.40
    POSITIVE LOGITS
     %=
    0.50
     =
    0.49
     NOT
    0.47
    idual
    0.46
    |=
    0.46
     |=
    0.44
     /=
    0.43
    ]&
    0.43
     =~
    0.41
    &(
    0.41
    Activations Density 0.000%

    No Known Activations