© 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. 51234
    Prev
    Next
    INDEX
    Explanations

    rooibos

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

    based on

    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
     општи
    0.49
     योर
    0.48
     ($_
    0.46
     estatales
    0.45
     (_,
    0.44
    俚
    0.44
    ્ઞ
    0.43
     स्टेट
    0.43
    яў
    0.43
    λλά
    0.42
    POSITIVE LOGITS
    কর
    0.46
     cari
    0.44
     Cari
    0.43
     od
    0.42
    cari
    0.42
     abuses
    0.42
     abuse
    0.41
    rika
    0.40
    </em>
    0.40
     arthritis
    0.40
    Activations Density 0.001%

    No Known Activations