© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 13687
    Prev
    Next
    INDEX
    Explanations

    also, bands, answer, stop, Turtle, order

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     balloon
    0.45
     Balloon
    0.40
    ，
    0.39
     d
    0.38
     дій
    0.38
    ،
    0.38
     tiež
    0.37
     week
    0.37
     also
    0.37
     –
    0.37
    POSITIVE LOGITS
     kontakt
    0.45
     thisStudent
    0.45
    Hozz
    0.44
    ought
    0.43
     kaliteli
    0.43
    iwers
    0.42
     þis
    0.42
     kontaktu
    0.42
    atzen
    0.42
     legyen
    0.42
    Activations Density 0.000%

    No Known Activations