© 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. 90058
    Prev
    Next
    INDEX
    Explanations

    domain names

    np_acts-logits-general · gemini-2.5-flash-lite

    actions and changes

    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
    𒊩
    0.48
    <0xA2>
    0.46
    fton
    0.44
     aggregating
    0.42
     顔
    0.42
    পী
    0.42
    𒇻
    0.41
     facet
    0.41
     पूर्वक
    0.40
     mog
    0.40
    POSITIVE LOGITS
    O
    0.53
    I
    0.51
    инг
    0.50
     в
    0.50
    U
    0.50
    อ
    0.49
    卄
    0.49
    Elite
    0.49
    P
    0.49
    Pant
    0.49
    Activations Density 0.001%

    No Known Activations