© 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. 238621
    Prev
    Next
    INDEX
    Explanations

    trotting down

    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
     সংকো
    0.49
     Vật
    0.48
    酯
    0.48
     కొన
    0.48
    設
    0.48
    𝟯
    0.47
    ສຸດ
    0.46
    中部
    0.46
     भै
    0.45
     ఇచ్చ
    0.45
    POSITIVE LOGITS
    '
    0.59
     enmity
    0.50
     to
    0.50
     professor
    0.47
     offend
    0.47
     contends
    0.46
     posits
    0.45
     is
    0.45
     directeur
    0.45
    to
    0.44
    Activations Density 0.000%

    No Known Activations