© 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. 16-GEMMASCOPE-2-RES-262K
    7. 9520
    Prev
    Next
    INDEX
    Explanations

    css stylesheet links

    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_16_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
    ের
    0.65
    taxi
    0.57
    is
    0.57
    to
    0.54
    ی
    0.53
    aula
    0.52
    aider
    0.52
    i
    0.52
    tain
    0.51
    اعر
    0.51
    POSITIVE LOGITS
     величина
    0.48
    糁
    0.46
     천
    0.46
     공
    0.44
     goed
    0.43
     בר
    0.43
    ಿಕೊಂಡು
    0.42
    ೃಷ್ಣ
    0.41
    })$
    0.41
     미
    0.41
    Activations Density 0.002%

    No Known Activations