© 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. 31-GEMMASCOPE-2-RES-262K
    7. 77989
    Prev
    Next
    INDEX
    Explanations

    social progress

    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_31_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
     u
    0.50
     الس
    0.50
     S
    0.48
    licas
    0.48
     Moy
    0.47
    msup
    0.47
    amar
    0.46
     d
    0.45
     Arch
    0.45
     Kall
    0.45
    POSITIVE LOGITS
     اینڈ
    0.56
     PWMB
    0.49
    غیر
    0.46
    fNil
    0.45
     தொகை
    0.45
     potrebbe
    0.44
    انیہ
    0.44
     altercation
    0.43
    곧
    0.43
     سوچ
    0.43
    Activations Density 0.004%

    No Known Activations