© 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-65K
    7. 51144
    Prev
    Next
    INDEX
    Explanations

    establish and what follows

    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_65k_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
    يل
    0.88
    3
    0.77
    4
    0.76
    \
    0.72
     of
    0.69
    ك
    0.69
    9
    0.68
    6
    0.66
     jeopard
    0.65
    كان
    0.62
    POSITIVE LOGITS
    establishing
    1.02
    Establishing
    0.98
     Establish
    0.98
    establish
    0.98
     Establishing
    0.97
    established
    0.95
     establishing
    0.94
     establish
    0.91
     established
    0.87
    is
    0.86
    Activations Density 0.039%

    No Known Activations