© 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. 142109
    Prev
    Next
    INDEX
    Explanations

    individual possessing

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

    either direct

    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
    árny
    0.48
    用
    0.47
    hnt
    0.47
    يت
    0.44
    Italian
    0.42
    صار
    0.41
    يا
    0.41
    ಹ
    0.41
     algunos
    0.40
    CString
    0.40
    POSITIVE LOGITS
     โอ้
    0.55
    fails
    0.52
    评审
    0.48
    ຫຼື
    0.47
     FAIL
    0.46
    biotic
    0.46
    彧
    0.46
    ธุรกิจ
    0.46
     ರಚ
    0.46
     निपट
    0.45
    Activations Density 0.001%

    No Known Activations