© 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. 16-GEMMASCOPE-2-RES-262K
    4. 103857
    Prev
    Next
    INDEX
    Explanations

    literary techniques and stylistic choices

    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
    S
    0.54
    ご飯
    0.53
     SAND
    0.50
    +.
    0.49
    饭
    0.48
     Angela
    0.47
    あなたが
    0.47
    در
    0.46
    كتب
    0.46
     EDU
    0.46
    POSITIVE LOGITS
     поверхности
    0.61
     στοι
    0.60
     textural
    0.58
     ვერ
    0.57
     expedient
    0.56
     Entfer
    0.56
    otipos
    0.55
     diction
    0.54
    襟
    0.54
     பார்வை
    0.54
    Activations Density 0.072%

    No Known Activations