© 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. 23319
    Prev
    Next
    INDEX
    Explanations

    disintegration state, financial macro, remarriage

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

    following prompt instructions

    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
    к
    0.46
     Alzheimer
    0.44
     Accom
    0.43
    .).
    0.43
     Aper
    0.43
    滉
    0.43
     стоимо
    0.42
     дизай
    0.42
    .
    0.42
     Eats
    0.42
    POSITIVE LOGITS
     decrypted
    0.51
     cipher
    0.47
     decrypt
    0.45
     defied
    0.44
    ů
    0.44
    𒉺
    0.43
     chiefly
    0.42
     enforces
    0.42
     withered
    0.42
     originates
    0.42
    Activations Density 0.000%

    No Known Activations