© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 1786
    Prev
    Next
    INDEX
    Explanations

    small, little, happy

    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
    IPC
    1.45
     IPC
    1.29
     ipc
    1.25
     antiviral
    1.23
     brok
    1.22
     $((
    1.21
     ginh
    1.19
    }|$
    1.18
     (‘
    1.18
     Cooks
    1.18
    POSITIVE LOGITS
    aughty
    1.01
    Small
    0.92
     Little
    0.92
    happy
    0.91
     Happy
    0.91
     Begin
    0.91
    Begin
    0.90
    Little
    0.90
     Small
    0.90
    Without
    0.89
    Activations Density 0.155%

    No Known Activations