© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 280
    Prev
    Next
    INDEX
    Explanations

    blending words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
     وعلى
    1.38
    ot
    1.19
    v
    1.09
    itus
    0.94
    ities
    0.93
    og
    0.92
    ва
    0.92
     उम्र
    0.86
     uncovered
    0.86
    itian
    0.85
    POSITIVE LOGITS
    ścic
    1.55
    tól
    1.36
    𝘆
    1.34
    ﻟ
    1.27
    anju
    1.27
    Bran
    1.27
    ৫
    1.26
    𝘀
    1.21
    ্ড
    1.18
    徃
    1.18
    Activations Density 0.005%

    No Known Activations