© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 3897
    Prev
    Next
    INDEX
    Explanations

    programmer, developer, C++ dev

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
    semer
    2.80
     семья
    2.76
     والد
    2.68
    intendent
    2.63
    俗
    2.60
    ويض
    2.57
     该
    2.57
    وال
    2.56
     speak
    2.53
    お
    2.49
    POSITIVE LOGITS
    atte
    0.80
    ấu
    0.74
    tti
    0.68
     miejscu
    0.67
    atti
    0.65
    atto
    0.64
    哆
    0.51
    nych
    0.48
     bawah
    0.47
    身上
    0.47
    Activations Density 0.025%

    No Known Activations