© 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. 100187
    Prev
    Next
    INDEX
    Explanations

    Current LLMs, reasoning

    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
    Ი
    0.49
    ভূমির
    0.49
     codeword
    0.48
     codewords
    0.48
    ிலே
    0.47
    創新
    0.47
    κη
    0.47
     modalidad
    0.47
     momentos
    0.47
    𝗋
    0.47
    POSITIVE LOGITS
     brain
    0.45
     wür
    0.44
    .
    0.44
     garg
    0.42
     äl
    0.41
     popular
    0.41
     radio
    0.41
     dial
    0.40
    ).
    0.40
     กระ
    0.40
    Activations Density 0.004%

    No Known Activations