© 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. 3905
    Prev
    Next
    INDEX
    Explanations

    song after song

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

    a list

    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
    ির
    0.26
    ir
    0.26
    and
    0.24
    োতে
    0.24
    empty
    0.24
    it
    0.23
     I
    0.23
     Při
    0.23
    ↵
    0.23
    ्य
    0.23
    POSITIVE LOGITS
     podido
    0.20
     empresarios
    0.20
     empresario
    0.20
     jurispr
    0.20
     […]
    0.19
    ктор
    0.19
     sociedade
    0.19
     repatri
    0.19
    썽
    0.18
     legisl
    0.18
    Activations Density 4.364%

    No Known Activations