© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 13585
    Prev
    Next
    INDEX
    Explanations

    should not be

    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
    蔵
    0.38
    ethane
    0.37
     Lovers
    0.36
     tabular
    0.36
    口味
    0.36
    玉
    0.36
    XY
    0.35
    9
    0.35
    ៃ
    0.35
    GY
    0.34
    POSITIVE LOGITS
     जिक्र
    0.49
     nejsou
    0.49
     wohl
    0.46
     nicht
    0.46
     değildir
    0.45
     seguir
    0.44
     wszel
    0.44
    ties
    0.44
     envis
    0.44
    மேலும்
    0.44
    Activations Density 0.000%

    No Known Activations