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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 98497
    Prev
    Next
    INDEX
    Explanations

    safety instructions

    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_40_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
    _-
    0.41
     nacido
    0.39
     ausge
    0.39
     automáticamente
    0.38
    Boost
    0.37
     uitge
    0.37
     প্রমাণিত
    0.37
     erhält
    0.37
     Modes
    0.37
     eigenes
    0.37
    POSITIVE LOGITS
    媺
    0.39
     ஆற
    0.39
     часть
    0.38
    esth
    0.37
     deel
    0.37
     cath
    0.35
    -->
    0.35
    浴
    0.35
    ोम
    0.34
    ond
    0.34
    Activations Density 0.000%

    No Known Activations