© 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. 79421
    Prev
    Next
    INDEX
    Explanations

    phrases and follow-on words

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

    loan into

    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
     വിൽപ്പന
    0.44
    ček
    0.43
     Leibniz
    0.43
     പ്രവർ
    0.43
    otive
    0.42
    驥
    0.42
    catalyzed
    0.42
     Ive
    0.42
    راحی
    0.42
    を含む
    0.41
    POSITIVE LOGITS
    SIM
    0.50
    半年
    0.47
     antigua
    0.45
    íes
    0.45
    욤
    0.44
    nbs
    0.43
     índices
    0.43
     அனுப்ப
    0.42
    ㄤ
    0.42
     қи
    0.42
    Activations Density 0.000%

    No Known Activations