© 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. 117012
    Prev
    Next
    INDEX
    Explanations

    Legal procedures and registration

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

    referring to lists or examples

    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
     pouls
    0.45
     අඩු
    0.44
    śred
    0.44
     kalp
    0.44
    糀
    0.43
    দ
    0.43
     życia
    0.42
    と同様
    0.42
     Cũng
    0.42
     Phương
    0.42
    POSITIVE LOGITS
    Fork
    0.44
    Publications
    0.43
    _
    0.41
     consulta
    0.40
    RegisterClass
    0.40
     _:
    0.40
     regist
    0.39
    _);
    0.39
    Drawable
    0.39
    ClickListener
    0.38
    Activations Density 0.001%

    No Known Activations