© 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. 231742
    Prev
    Next
    INDEX
    Explanations

    languages and programming

    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
    ܦ
    0.47
     skaters
    0.46
     Jackie
    0.45
     चार्ट
    0.44
     ایالات
    0.44
     scream
    0.44
     가족
    0.44
     لندن
    0.44
    𝓭
    0.43
     kiss
    0.43
    POSITIVE LOGITS
    ıntı
    0.49
    ланд
    0.44
    ipkan
    0.43
    ঞ্জার
    0.43
    يمة
    0.43
    Handsome
    0.42
    onDidChange
    0.42
    Autowired
    0.41
    ંદ્ર
    0.41
    onResume
    0.41
    Activations Density 0.001%

    No Known Activations