© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 205097
    Prev
    Next
    INDEX
    Explanations

    due to / because of

    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_37_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
     Greetings
    0.38
    ጅ
    0.37
    </tbody>
    0.35
    AGRAM
    0.35
     Idani
    0.35
     proportionality
    0.34
    させて
    0.33
     nitidus
    0.32
     Pasand
    0.32
     Darstellung
    0.32
    POSITIVE LOGITS
     due
    2.41
     vanwege
    2.25
    due
    2.20
    因
    2.19
     debido
    2.16
     بسبب
    2.16
    Due
    2.14
     devido
    2.13
    由于
    2.11
     zbog
    2.11
    Activations Density 0.165%

    No Known Activations