© 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. 58631
    Prev
    Next
    INDEX
    Explanations

    brewery considers

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

    break 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
    ли
    0.55
    Accessories
    0.50
    With
    0.49
    ก
    0.49
    Important
    0.48
    Cu
    0.48
    к
    0.47
    Tenemos
    0.47
    2
    0.47
    Black
    0.46
    POSITIVE LOGITS
     feest
    0.41
     പറയുന്നത്
    0.40
    放棄
    0.40
     remon
    0.40
     osoby
    0.40
     osób
    0.39
     personer
    0.39
     grunds
    0.39
     expectation
    0.39
     dissipation
    0.39
    Activations Density 0.000%

    No Known Activations