© 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-65K
    7. 49337
    Prev
    Next
    INDEX
    Explanations

    training data and parameters

    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_65k_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
    icmp
    0.44
     Rotor
    0.41
     GPUs
    0.39
     раза
    0.39
     VLAN
    0.38
     VLC
    0.36
    蘄
    0.36
     conditioners
    0.36
     ICP
    0.36
     mics
    0.36
    POSITIVE LOGITS
    ismatch
    0.49
    dataset
    0.46
     noisy
    0.41
     Norway
    0.41
    verbose
    0.40
    动画
    0.40
    <0xA2>
    0.40
    Norway
    0.39
    動畫
    0.39
    polynomial
    0.39
    Activations Density 0.052%

    No Known Activations