© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 3525
    Prev
    Next
    INDEX
    Explanations

    theoretical perspective, or initialization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    an
    0.53
    on
    0.48
    onka
    0.46
    рида
    0.46
     infek
    0.46
     инфек
    0.45
    ἧ
    0.45
     as
    0.44
     अधिकारी
    0.44
     mitral
    0.44
    POSITIVE LOGITS
    その他の
    0.48
    uí
    0.47
     seguenti
    0.46
     कामगिरी
    0.46
    IFIER
    0.45
     themed
    0.43
    ائیو
    0.43
     निभाई
    0.42
    iesi
    0.42
    دأ
    0.42
    Activations Density 0.000%

    No Known Activations