© 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. 19964
    Prev
    Next
    INDEX
    Explanations

    more capable, find Lena

    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
     дене
    0.46
    ંબા
    0.44
     nisid
    0.41
     Rxe
    0.41
     консу
    0.40
    бурга
    0.40
    视野
    0.40
    饲
    0.40
    "।
    0.39
    ligo
    0.39
    POSITIVE LOGITS
    ––
    0.41
     shaping
    0.40
     المؤ
    0.39
    cję
    0.39
     Shaping
    0.38
    €”
    0.38
     symb
    0.38
     ag
    0.37
     Hasil
    0.37
    ]),
    0.36
    Activations Density 0.000%

    No Known Activations