© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 244712
    Prev
    Next
    INDEX
    Explanations

    car either

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تل
    0.49
    ቹን
    0.47
    voluntary
    0.45
    ⟥
    0.45
    }^{+}+
    0.45
    exclusions
    0.43
     pegatina
    0.43
    ABLES
    0.43
    ផ្ល
    0.43
    遉
    0.43
    POSITIVE LOGITS
    า
    0.59
     has
    0.52
     первым
    0.51
    has
    0.46
    ou
    0.46
    ik
    0.45
     FT
    0.45
    ंक
    0.44
    ic
    0.44
    ́t
    0.44
    Activations Density 0.001%

    No Known Activations