© 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
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 105921
    Prev
    Next
    INDEX
    Explanations

    referring to him, emojis, miles, failures

    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_16_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
     of
    0.86
    of
    0.82
     to
    0.80
     äh
    0.73
     elegante
    0.72
     and
    0.72
     և
    0.71
    ;}
    0.70
    г
    0.70
    it
    0.70
    POSITIVE LOGITS
     contesto
    0.70
     pousse
    0.68
    ᱼ
    0.67
     sepsis
    0.65
     جنہوں
    0.65
     déput
    0.65
     huis
    0.64
     очередь
    0.64
     pensa
    0.64
    in
    0.63
    Activations Density 0.000%

    No Known Activations