© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 23456
    Prev
    Next
    INDEX
    Explanations

    tire pressure, alignment, pinch

    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_all/layer_41_width_262k_l0_big
    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
     rubbers
    0.51
     tyres
    0.49
     rubber
    0.46
     engine
    0.44
    rubber
    0.43
     इंजन
    0.43
     tires
    0.42
    牰
    0.39
    OVERRIDES
    0.39
     wheels
    0.39
    POSITIVE LOGITS
     TP
    0.60
     alignment
    0.55
    TP
    0.54
     Alignment
    0.52
    Align
    0.50
     Balancing
    0.49
    alignment
    0.47
    Alignment
    0.47
     align
    0.46
     Align
    0.46
    Activations Density 0.002%

    No Known Activations