© 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. 145531
    Prev
    Next
    INDEX
    Explanations

    communication and finance terms

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

    list, song, writing, AI

    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
    ून्य
    0.45
     cerebellar
    0.45
     axonal
    0.45
    ]}$.
    0.44
     theoret
    0.42
     paradig
    0.41
     limita
    0.41
     grandiose
    0.40
     Cáceres
    0.40
    ]。
    0.40
    POSITIVE LOGITS
    +
    0.55
     花
    0.51
    \&
    0.45
     अक्सर
    0.44
    ఇ
    0.44
     Backpack
    0.43
    +"
    0.43
     通
    0.43
     麻
    0.43
    ;
    0.43
    Activations Density 0.000%

    No Known Activations