© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 4456
    Prev
    Next
    INDEX
    Explanations

    I know / She forecast / I was / Everybody has / This magnificent

    np_acts-logits-general · gemini-2.5-flash-lite

    first-person or third-person statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     نیز
    0.54
    }$.
    0.51
     다음과
    0.50
     ומ
    0.46
     או
    0.45
    ת
    0.44
     גם
    0.42
    ר
    0.42
     נוס
    0.41
    또한
    0.41
    POSITIVE LOGITS
     [
    0.57
    ,”
    0.51
     everybody
    0.51
     people
    0.50
     basically
    0.49
    ,’’
    0.47
     absolutely
    0.47
     definitely
    0.46
     really
    0.45
     came
    0.45
    Activations Density 0.260%

    No Known Activations