© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 143650
    Prev
    Next
    INDEX
    Explanations

    section separators

    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
    н
    0.55
    Y
    0.53
    et
    0.52
    к
    0.51
     famously
    0.47
     invade
    0.47
     other
    0.45
     */
    0.45
     clumsy
    0.45
     arguably
    0.45
    POSITIVE LOGITS
     رام
    0.50
    یوں
    0.48
    亿元
    0.45
     तसेच
    0.44
    فو
    0.43
    ivos
    0.43
     पुढे
    0.41
    рів
    0.41
    激励
    0.41
    왔
    0.40
    Activations Density 0.001%

    No Known Activations