© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 90747
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by verbs

    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_262k_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
    ጀት
    0.50
    चा
    0.50
    ի
    0.46
    גר
    0.46
    형
    0.46
    袈
    0.46
    ダ
    0.46
    蝟
    0.45
     aplatis
    0.45
    髂
    0.45
    POSITIVE LOGITS
    0.59
     says
    0.58
     They
    0.57
     said
    0.52
    They
    0.52
     họ
    0.47
     they
    0.46
     wrote
    0.45
     మాట్లాడుతూ
    0.44
     coached
    0.44
    Activations Density 0.026%

    No Known Activations