© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 26451
    Prev
    Next
    INDEX
    Explanations

    reach or reaching

    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_all/layer_41_width_262k_l0_big
    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
     தாம்
    0.39
    દાવાદ
    0.38
    اندان
    0.37
    మంలో
    0.37
    জ্ঞা
    0.36
     布
    0.36
     Carn
    0.35
     काळ
    0.35
    布
    0.35
    грани
    0.35
    POSITIVE LOGITS
     reach
    2.50
     reaches
    2.45
     reaching
    2.44
     reached
    2.27
    到达
    2.19
    Reach
    2.19
    reach
    2.14
     Reach
    2.11
    reaching
    2.08
    到達
    1.98
    Activations Density 0.002%

    No Known Activations