© 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. 155465
    Prev
    Next
    INDEX
    Explanations

    chemicals and computing

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

    of, behind, yet, or

    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
     cadeau
    0.51
    }+\
    0.45
    يل
    0.45
     lành
    0.45
    };
    0.44
    ('/');
    0.44
    خواه
    0.44
     staples
    0.42
     отвечает
    0.42
    }/\
    0.42
    POSITIVE LOGITS
     CHEMICAL
    0.46
     Chemical
    0.45
     Computing
    0.44
     टेक्निकल
    0.44
     শোক
    0.43
     Chemicals
    0.43
     VIII
    0.41
     কর্মকর্তার
    0.41
    rivate
    0.41
     Generic
    0.40
    Activations Density 0.001%

    No Known Activations