© 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. 40-GEMMASCOPE-2-RES-262K
    7. 10453
    Prev
    Next
    INDEX
    Explanations

    when followed by specific phrases

    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_40_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
     //.
    0.41
    ర్కొ
    0.38
     candidacy
    0.38
     keseluruhan
    0.37
     रस
    0.35
    andolo
    0.35
     harb
    0.35
     ກ
    0.35
     keyed
    0.34
     哦
    0.34
    POSITIVE LOGITS
    soever
    0.53
    ce
    0.51
     autocomplete
    0.48
     did
    0.47
    abouts
    0.44
    EVER
    0.42
    by
    0.41
    Is
    0.41
    should
    0.40
    Ꮒ
    0.40
    Activations Density 0.007%

    No Known Activations