© 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. 50518
    Prev
    Next
    INDEX
    Explanations

    This is called

    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
     contraseña
    0.41
    icel
    0.40
     />';
    0.39
    埚
    0.37
     потребо
    0.36
    মাংস
    0.36
     നാല
    0.35
    सात
    0.35
    Მ
    0.35
     пяти
    0.35
    POSITIVE LOGITS
     sogenannten
    1.63
     called
    1.55
     tzv
    1.54
     sogenannte
    1.54
     sogen
    1.50
    稱為
    1.46
     cosidd
    1.43
     tzw
    1.42
     termed
    1.40
    called
    1.34
    Activations Density 0.358%

    No Known Activations