© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 247034
    Prev
    Next
    INDEX
    Explanations

    commencement, continuing, or commencement

    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
    ר
    0.49
     뿐
    0.42
     욕
    0.42
    וח
    0.41
    AMBI
    0.41
     궁금
    0.41
     খি
    0.41
    ز
    0.41
    jp
    0.40
     RADIO
    0.40
    POSITIVE LOGITS
    }^{*}
    0.46
     commencement
    0.46
     commencing
    0.45
     acceptable
    0.45
     prepping
    0.44
    或
    0.43
     adjustment
    0.43
    ដែលមាន
    0.42
                            
    0.42
     혹은
    0.42
    Activations Density 0.002%

    No Known Activations