© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 22570
    Prev
    Next
    INDEX
    Explanations

    "really" as an intensifier

    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
    که
    0.87
    ER
    0.86
    یم
    0.85
    AL
    0.78
    AT
    0.76
    dı
    0.76
    r
    0.75
    OF
    0.74
    ка
    0.74
    EL
    0.74
    POSITIVE LOGITS
    يل
    0.76
    ير
    0.71
    知道
    0.71
    什么
    0.70
    ان
    0.67
    ation
    0.65
    ég
    0.65
    的目标
    0.65
     ఉన్న
    0.64
    的研究
    0.63
    Activations Density 0.025%

    No Known Activations