© 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. 16-GEMMASCOPE-2-RES-262K
    7. 88546
    Prev
    Next
    INDEX
    Explanations

    Ansible playbooks and balloons

    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
     trama
    0.57
     també
    0.55
     préférable
    0.54
     मोठ्या
    0.53
    ۾
    0.53
     hatches
    0.52
     também
    0.52
    两个
    0.52
    今日
    0.52
     restant
    0.52
    POSITIVE LOGITS
     I
    0.54
     She
    0.51
    Sec
    0.51
     Sh
    0.50
    Werk
    0.50
    Separ
    0.49
    Typography
    0.48
    Rank
    0.48
    Pure
    0.48
    Discount
    0.47
    Activations Density 0.000%

    No Known Activations