© 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. 128819
    Prev
    Next
    INDEX
    Explanations

    states, locations, or comparisons

    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
    ⚉
    0.51
     sucre
    0.51
    س
    0.48
     sculptural
    0.47
     dumplings
    0.46
     relacionamento
    0.46
    삶
    0.45
    ፨
    0.45
    चाकी
    0.45
    מס
    0.45
    POSITIVE LOGITS
    oj
    0.49
     $\
    0.44
     ((
    0.43
     Science
    0.43
     $(
    0.42
     Flood
    0.42
     (_
    0.41
     Entrance
    0.41
    uje
    0.40
     $(\
    0.40
    Activations Density 0.004%

    No Known Activations