© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 261360
    Prev
    Next
    INDEX
    Explanations

    say pronoun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_5_width_262k_l0_small_affine
    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
    }
    1.39
    у
    1.38
     powied
    1.34
    お
    1.30
     aplatis
    1.26
    quela
    1.24
    ların
    1.20
     piccole
    1.20
    деся
    1.19
    .}
    1.16
    POSITIVE LOGITS
    krank
    1.24
    ia
    1.20
    y
    1.20
    ן
    1.19
    h
    1.11
    iv
    1.10
    ंग
    1.03
    دا
    1.02
    hj
    1.02
    ні
    1.01
    Activations Density 0.002%

    No Known Activations